Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3382 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3552. Min Range: -8.3552
Max Act: 8.3552. Min Act: -0.1700
Data Index: 8041121 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3552. Min Range: -8.3552
Max Act: 8.1677. Min Act: -0.1700
Data Index: 4518957 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3552. Min Range: -8.3552
Max Act: 8.0427. Min Act: -0.1700
Data Index: 1911770 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3552. Min Range: -8.3552
Max Act: 8.1052. Min Act: -0.1700
Data Index: 4434095 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3552. Min Range: -8.3552
Max Act: 7.9177. Min Act: -0.1700
Data Index: 5802840 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3552. Min Range: -8.3552
Max Act: 7.8552. Min Act: -0.1700
Data Index: 5229184 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3552. Min Range: -8.3552
Max Act: 7.7927. Min Act: -0.1700
Data Index: 7007433 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3552. Min Range: -8.3552
Max Act: 7.7927. Min Act: -0.1700
Data Index: 4964495 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3552. Min Range: -8.3552
Max Act: 7.7927. Min Act: -0.1700
Data Index: 4756705 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3552. Min Range: -8.3552
Max Act: 7.7927. Min Act: -0.1700
Data Index: 6667547 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3552. Min Range: -8.3552
Max Act: 7.7927. Min Act: -0.1700
Data Index: 3166190 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3552. Min Range: -8.3552
Max Act: 7.7927. Min Act: -0.1700
Data Index: 6152491 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3552. Min Range: -8.3552
Max Act: 7.7302. Min Act: -0.1700
Data Index: 3309518 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3552. Min Range: -8.3552
Max Act: 7.7302. Min Act: -0.1700
Data Index: 5316346 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3552. Min Range: -8.3552
Max Act: 7.7302. Min Act: -0.1700
Data Index: 307040 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3552. Min Range: -8.3552
Max Act: 7.7302. Min Act: -0.1700
Data Index: 4199895 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3552. Min Range: -8.3552
Max Act: 7.7302. Min Act: -0.1700
Data Index: 6010243 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3552. Min Range: -8.3552
Max Act: 7.6989. Min Act: -0.1700
Data Index: 2968500 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3552. Min Range: -8.3552
Max Act: 7.6989. Min Act: -0.1700
Data Index: 8719663 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3552. Min Range: -8.3552
Max Act: 7.6677. Min Act: -0.1700
Data Index: 6580567 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19