Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1358 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6246. Min Range: -3.6246
Max Act: 3.6246. Min Act: -0.1700
Data Index: 3164972 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6246. Min Range: -3.6246
Max Act: 3.5150. Min Act: -0.1700
Data Index: 762537 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6246. Min Range: -3.6246
Max Act: 3.4994. Min Act: -0.1700
Data Index: 2913947 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6246. Min Range: -3.6246
Max Act: 3.4524. Min Act: -0.1700
Data Index: 4410944 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6246. Min Range: -3.6246
Max Act: 3.4524. Min Act: -0.1700
Data Index: 8455938 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6246. Min Range: -3.6246
Max Act: 3.4054. Min Act: -0.1700
Data Index: 2391657 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6246. Min Range: -3.6246
Max Act: 3.4210. Min Act: -0.1700
Data Index: 1080779 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6246. Min Range: -3.6246
Max Act: 3.4054. Min Act: -0.1700
Data Index: 5740800 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6246. Min Range: -3.6246
Max Act: 3.3897. Min Act: -0.1700
Data Index: 6596017 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6246. Min Range: -3.6246
Max Act: 3.3897. Min Act: -0.1700
Data Index: 8430137 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6246. Min Range: -3.6246
Max Act: 3.3897. Min Act: -0.1700
Data Index: 157599 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6246. Min Range: -3.6246
Max Act: 3.3583. Min Act: -0.1700
Data Index: 3787343 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6246. Min Range: -3.6246
Max Act: 3.3583. Min Act: -0.1700
Data Index: 3198371 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6246. Min Range: -3.6246
Max Act: 3.3583. Min Act: -0.1700
Data Index: 1940221 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6246. Min Range: -3.6246
Max Act: 3.3426. Min Act: -0.1700
Data Index: 2016810 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6246. Min Range: -3.6246
Max Act: 3.3269. Min Act: -0.1700
Data Index: 2836648 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6246. Min Range: -3.6246
Max Act: 3.3269. Min Act: -0.1700
Data Index: 5378831 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6246. Min Range: -3.6246
Max Act: 3.3112. Min Act: -0.1700
Data Index: 8465654 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6246. Min Range: -3.6246
Max Act: 3.3112. Min Act: -0.1700
Data Index: 285600 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6246. Min Range: -3.6246
Max Act: 3.2955. Min Act: -0.1700
Data Index: 6295358 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19