Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3478 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4239. Min Range: -7.4239
Max Act: 7.4239. Min Act: -0.1700
Data Index: 6985994 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4239. Min Range: -7.4239
Max Act: 7.3927. Min Act: -0.1700
Data Index: 8582633 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4239. Min Range: -7.4239
Max Act: 7.3302. Min Act: -0.1700
Data Index: 4714394 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4239. Min Range: -7.4239
Max Act: 7.2364. Min Act: -0.1700
Data Index: 2195402 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4239. Min Range: -7.4239
Max Act: 7.2052. Min Act: -0.1700
Data Index: 7825158 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4239. Min Range: -7.4239
Max Act: 7.2364. Min Act: -0.1700
Data Index: 386105 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4239. Min Range: -7.4239
Max Act: 7.1739. Min Act: -0.1700
Data Index: 5337249 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4239. Min Range: -7.4239
Max Act: 7.0489. Min Act: -0.1700
Data Index: 8475106 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4239. Min Range: -7.4239
Max Act: 6.9864. Min Act: -0.1700
Data Index: 1915548 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4239. Min Range: -7.4239
Max Act: 6.9552. Min Act: -0.1700
Data Index: 6360359 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4239. Min Range: -7.4239
Max Act: 6.9864. Min Act: -0.1700
Data Index: 8523973 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4239. Min Range: -7.4239
Max Act: 6.9864. Min Act: -0.1700
Data Index: 4682603 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4239. Min Range: -7.4239
Max Act: 6.9552. Min Act: -0.1700
Data Index: 7246928 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4239. Min Range: -7.4239
Max Act: 6.9552. Min Act: -0.1700
Data Index: 6477033 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4239. Min Range: -7.4239
Max Act: 6.9552. Min Act: -0.1700
Data Index: 4788729 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4239. Min Range: -7.4239
Max Act: 6.9552. Min Act: -0.1700
Data Index: 3017331 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4239. Min Range: -7.4239
Max Act: 6.9552. Min Act: -0.1700
Data Index: 7156418 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4239. Min Range: -7.4239
Max Act: 6.8927. Min Act: -0.1700
Data Index: 2920269 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4239. Min Range: -7.4239
Max Act: 6.8927. Min Act: -0.1700
Data Index: 2895759 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4239. Min Range: -7.4239
Max Act: 6.8614. Min Act: -0.1700
Data Index: 8763966 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19