Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3892 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8458. Min Range: -2.8458
Max Act: 2.8458. Min Act: -0.1700
Data Index: 5347312 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8458. Min Range: -2.8458
Max Act: 2.8140. Min Act: -0.1700
Data Index: 574017 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8458. Min Range: -2.8458
Max Act: 2.8299. Min Act: -0.1700
Data Index: 4065498 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8458. Min Range: -2.8458
Max Act: 2.7502. Min Act: -0.1700
Data Index: 7699756 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8458. Min Range: -2.8458
Max Act: 2.7502. Min Act: -0.1700
Data Index: 1618539 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8458. Min Range: -2.8458
Max Act: 2.7183. Min Act: -0.1700
Data Index: 1515907 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8458. Min Range: -2.8458
Max Act: 2.7023. Min Act: -0.1700
Data Index: 8462976 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8458. Min Range: -2.8458
Max Act: 2.7023. Min Act: -0.1700
Data Index: 8317503 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8458. Min Range: -2.8458
Max Act: 2.6863. Min Act: -0.1700
Data Index: 4979427 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8458. Min Range: -2.8458
Max Act: 2.6863. Min Act: -0.1700
Data Index: 5571428 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8458. Min Range: -2.8458
Max Act: 2.6863. Min Act: -0.1700
Data Index: 3808356 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8458. Min Range: -2.8458
Max Act: 2.6863. Min Act: -0.1700
Data Index: 5138890 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8458. Min Range: -2.8458
Max Act: 2.6863. Min Act: -0.1700
Data Index: 6306273 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8458. Min Range: -2.8458
Max Act: 2.6703. Min Act: -0.1700
Data Index: 8356334 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8458. Min Range: -2.8458
Max Act: 2.6703. Min Act: -0.1700
Data Index: 6942527 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8458. Min Range: -2.8458
Max Act: 2.6703. Min Act: -0.1700
Data Index: 5906591 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8458. Min Range: -2.8458
Max Act: 2.6703. Min Act: -0.1700
Data Index: 1258566 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8458. Min Range: -2.8458
Max Act: 2.6382. Min Act: -0.1700
Data Index: 7631765 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8458. Min Range: -2.8458
Max Act: 2.6542. Min Act: -0.1700
Data Index: 6468654 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8458. Min Range: -2.8458
Max Act: 2.6542. Min Act: -0.1700
Data Index: 2343349 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19