Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4702 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4359. Min Range: -2.4359
Max Act: 2.4359. Min Act: -0.1700
Data Index: 1124600 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4359. Min Range: -2.4359
Max Act: 2.3870. Min Act: -0.1700
Data Index: 5711137 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4359. Min Range: -2.4359
Max Act: 2.3542. Min Act: -0.1700
Data Index: 1462876 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4359. Min Range: -2.4359
Max Act: 2.3706. Min Act: -0.1700
Data Index: 544368 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4359. Min Range: -2.4359
Max Act: 2.3870. Min Act: -0.1700
Data Index: 7394000 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4359. Min Range: -2.4359
Max Act: 2.3379. Min Act: -0.1700
Data Index: 1343326 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4359. Min Range: -2.4359
Max Act: 2.3542. Min Act: -0.1700
Data Index: 2190158 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4359. Min Range: -2.4359
Max Act: 2.3379. Min Act: -0.1700
Data Index: 3015165 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4359. Min Range: -2.4359
Max Act: 2.3542. Min Act: -0.1700
Data Index: 7954711 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4359. Min Range: -2.4359
Max Act: 2.3214. Min Act: -0.1700
Data Index: 1521927 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4359. Min Range: -2.4359
Max Act: 2.3214. Min Act: -0.1699
Data Index: 2183248 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4359. Min Range: -2.4359
Max Act: 2.3214. Min Act: -0.1700
Data Index: 3994799 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4359. Min Range: -2.4359
Max Act: 2.3050. Min Act: -0.1700
Data Index: 6701267 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4359. Min Range: -2.4359
Max Act: 2.3050. Min Act: -0.1700
Data Index: 5299561 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4359. Min Range: -2.4359
Max Act: 2.2886. Min Act: -0.1700
Data Index: 499911 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4359. Min Range: -2.4359
Max Act: 2.2886. Min Act: -0.1700
Data Index: 2825859 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4359. Min Range: -2.4359
Max Act: 2.2886. Min Act: -0.1700
Data Index: 4648875 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4359. Min Range: -2.4359
Max Act: 2.2886. Min Act: -0.1700
Data Index: 6195405 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4359. Min Range: -2.4359
Max Act: 2.3050. Min Act: -0.1700
Data Index: 5024974 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4359. Min Range: -2.4359
Max Act: 2.2390. Min Act: -0.1700
Data Index: 2299248 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19