Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2682 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8133. Min Range: -4.8133
Max Act: 4.8133. Min Act: -0.1700
Data Index: 7588971 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8133. Min Range: -4.8133
Max Act: 4.7508. Min Act: -0.1700
Data Index: 7872755 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8133. Min Range: -4.8133
Max Act: 4.7508. Min Act: -0.1700
Data Index: 465325 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8133. Min Range: -4.8133
Max Act: 4.7508. Min Act: -0.1700
Data Index: 3471439 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8133. Min Range: -4.8133
Max Act: 4.7508. Min Act: -0.1700
Data Index: 127290 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8133. Min Range: -4.8133
Max Act: 4.7508. Min Act: -0.1700
Data Index: 3095964 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8133. Min Range: -4.8133
Max Act: 4.7196. Min Act: -0.1700
Data Index: 768548 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8133. Min Range: -4.8133
Max Act: 4.7196. Min Act: -0.1700
Data Index: 4492398 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8133. Min Range: -4.8133
Max Act: 4.6883. Min Act: -0.1700
Data Index: 2194877 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8133. Min Range: -4.8133
Max Act: 4.6883. Min Act: -0.1700
Data Index: 2532564 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8133. Min Range: -4.8133
Max Act: 4.6883. Min Act: -0.1700
Data Index: 4725659 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8133. Min Range: -4.8133
Max Act: 4.6883. Min Act: -0.1700
Data Index: 6779276 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8133. Min Range: -4.8133
Max Act: 4.6883. Min Act: -0.1700
Data Index: 628946 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8133. Min Range: -4.8133
Max Act: 4.6883. Min Act: -0.1700
Data Index: 7362433 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8133. Min Range: -4.8133
Max Act: 4.7196. Min Act: -0.1700
Data Index: 7387563 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8133. Min Range: -4.8133
Max Act: 4.6883. Min Act: -0.1700
Data Index: 1871119 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8133. Min Range: -4.8133
Max Act: 4.6883. Min Act: -0.1700
Data Index: 7798662 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8133. Min Range: -4.8133
Max Act: 4.6883. Min Act: -0.1700
Data Index: 3734018 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8133. Min Range: -4.8133
Max Act: 4.6883. Min Act: -0.1626
Data Index: 295430 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8133. Min Range: -4.8133
Max Act: 4.6883. Min Act: -0.1700
Data Index: 8096934 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19