Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3987 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6340. Min Range: -5.6340
Max Act: 5.6340. Min Act: -0.1700
Data Index: 59483 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6340. Min Range: -5.6340
Max Act: 5.6340. Min Act: -0.1700
Data Index: 8575967 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6340. Min Range: -5.6340
Max Act: 5.6027. Min Act: -0.1700
Data Index: 2066444 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6340. Min Range: -5.6340
Max Act: 5.5715. Min Act: -0.1700
Data Index: 6262908 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6340. Min Range: -5.6340
Max Act: 5.5090. Min Act: -0.1700
Data Index: 8195679 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6340. Min Range: -5.6340
Max Act: 5.4777. Min Act: -0.1699
Data Index: 8770487 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6340. Min Range: -5.6340
Max Act: 5.4777. Min Act: -0.1700
Data Index: 947234 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6340. Min Range: -5.6340
Max Act: 5.5090. Min Act: -0.1700
Data Index: 8715931 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6340. Min Range: -5.6340
Max Act: 5.4777. Min Act: -0.1700
Data Index: 3247766 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6340. Min Range: -5.6340
Max Act: 5.4465. Min Act: -0.1700
Data Index: 3602712 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6340. Min Range: -5.6340
Max Act: 5.4465. Min Act: -0.1700
Data Index: 183867 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6340. Min Range: -5.6340
Max Act: 5.4152. Min Act: -0.1700
Data Index: 2662642 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6340. Min Range: -5.6340
Max Act: 5.4152. Min Act: -0.1700
Data Index: 898548 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6340. Min Range: -5.6340
Max Act: 5.4152. Min Act: -0.1700
Data Index: 2997762 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6340. Min Range: -5.6340
Max Act: 5.4152. Min Act: -0.1700
Data Index: 6170094 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6340. Min Range: -5.6340
Max Act: 5.4152. Min Act: -0.1700
Data Index: 1757469 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6340. Min Range: -5.6340
Max Act: 5.4152. Min Act: -0.1700
Data Index: 1381149 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6340. Min Range: -5.6340
Max Act: 5.4152. Min Act: -0.1700
Data Index: 2091795 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6340. Min Range: -5.6340
Max Act: 5.3840. Min Act: -0.1700
Data Index: 2729513 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6340. Min Range: -5.6340
Max Act: 5.3840. Min Act: -0.1700
Data Index: 553644 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19