Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4622 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4676. Min Range: -7.4676
Max Act: 7.4676. Min Act: -0.1700
Data Index: 3515154 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4676. Min Range: -7.4676
Max Act: 7.1239. Min Act: -0.1700
Data Index: 881469 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4676. Min Range: -7.4676
Max Act: 6.9989. Min Act: -0.1700
Data Index: 5029262 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4676. Min Range: -7.4676
Max Act: 6.9676. Min Act: -0.1700
Data Index: 1646254 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4676. Min Range: -7.4676
Max Act: 6.9676. Min Act: -0.1700
Data Index: 5427071 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4676. Min Range: -7.4676
Max Act: 6.9051. Min Act: -0.1700
Data Index: 6465192 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4676. Min Range: -7.4676
Max Act: 6.8739. Min Act: -0.1700
Data Index: 7213110 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4676. Min Range: -7.4676
Max Act: 6.8426. Min Act: -0.1700
Data Index: 2566734 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4676. Min Range: -7.4676
Max Act: 6.8739. Min Act: -0.1700
Data Index: 4281262 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4676. Min Range: -7.4676
Max Act: 6.8426. Min Act: -0.1700
Data Index: 1581601 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4676. Min Range: -7.4676
Max Act: 6.8114. Min Act: -0.1700
Data Index: 3588871 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4676. Min Range: -7.4676
Max Act: 6.8114. Min Act: -0.1700
Data Index: 3864305 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4676. Min Range: -7.4676
Max Act: 6.8114. Min Act: -0.1700
Data Index: 7130954 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4676. Min Range: -7.4676
Max Act: 6.7801. Min Act: -0.1700
Data Index: 3390058 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4676. Min Range: -7.4676
Max Act: 6.7801. Min Act: -0.1700
Data Index: 7964426 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4676. Min Range: -7.4676
Max Act: 6.7801. Min Act: -0.1700
Data Index: 3778050 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4676. Min Range: -7.4676
Max Act: 6.7801. Min Act: -0.1700
Data Index: 2583101 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4676. Min Range: -7.4676
Max Act: 6.7489. Min Act: -0.1700
Data Index: 2270986 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4676. Min Range: -7.4676
Max Act: 6.7176. Min Act: -0.1700
Data Index: 126024 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4676. Min Range: -7.4676
Max Act: 6.7176. Min Act: -0.1700
Data Index: 6381721 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19