Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1426 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 20.1739. Min Range: -20.1739
Max Act: 20.1739. Min Act: -0.1700
Data Index: 7867614 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 20.1739. Min Range: -20.1739
Max Act: 19.9239. Min Act: -0.1700
Data Index: 4315242 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 20.1739. Min Range: -20.1739
Max Act: 19.6739. Min Act: -0.1700
Data Index: 8237552 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 20.1739. Min Range: -20.1739
Max Act: 19.6739. Min Act: -0.1700
Data Index: 8765317 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 20.1739. Min Range: -20.1739
Max Act: 19.6739. Min Act: -0.1700
Data Index: 1837095 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 20.1739. Min Range: -20.1739
Max Act: 19.5489. Min Act: -0.1700
Data Index: 249340 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 20.1739. Min Range: -20.1739
Max Act: 19.6739. Min Act: -0.1700
Data Index: 8581026 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 20.1739. Min Range: -20.1739
Max Act: 19.5489. Min Act: -0.1700
Data Index: 2131182 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 20.1739. Min Range: -20.1739
Max Act: 19.4239. Min Act: -0.1700
Data Index: 3932558 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 20.1739. Min Range: -20.1739
Max Act: 19.2989. Min Act: -0.1700
Data Index: 6804684 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 20.1739. Min Range: -20.1739
Max Act: 19.4239. Min Act: -0.1700
Data Index: 4722561 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 20.1739. Min Range: -20.1739
Max Act: 19.2989. Min Act: -0.1700
Data Index: 5460975 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 20.1739. Min Range: -20.1739
Max Act: 19.2989. Min Act: -0.1700
Data Index: 3932559 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 20.1739. Min Range: -20.1739
Max Act: 19.1739. Min Act: -0.1700
Data Index: 3131557 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 20.1739. Min Range: -20.1739
Max Act: 19.4239. Min Act: -0.1700
Data Index: 1837091 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 20.1739. Min Range: -20.1739
Max Act: 19.1739. Min Act: -0.1700
Data Index: 2085204 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 20.1739. Min Range: -20.1739
Max Act: 18.9239. Min Act: -0.1700
Data Index: 3232337 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 20.1739. Min Range: -20.1739
Max Act: 19.1739. Min Act: -0.1700
Data Index: 694077 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 20.1739. Min Range: -20.1739
Max Act: 19.1739. Min Act: -0.1700
Data Index: 4478037 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 20.1739. Min Range: -20.1739
Max Act: 19.0489. Min Act: -0.1700
Data Index: 8082260 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19