Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4955 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.9379. Min Range: -7.9379
Max Act: 7.9379. Min Act: -0.1700
Data Index: 3848260 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9379. Min Range: -7.9379
Max Act: 7.9379. Min Act: -0.1700
Data Index: 880978 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9379. Min Range: -7.9379
Max Act: 7.7816. Min Act: -0.1700
Data Index: 8427204 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9379. Min Range: -7.9379
Max Act: 7.7816. Min Act: -0.1700
Data Index: 3737925 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9379. Min Range: -7.9379
Max Act: 7.7504. Min Act: -0.1700
Data Index: 5859826 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9379. Min Range: -7.9379
Max Act: 7.7191. Min Act: -0.1700
Data Index: 5504141 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9379. Min Range: -7.9379
Max Act: 7.6879. Min Act: -0.1700
Data Index: 6362798 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9379. Min Range: -7.9379
Max Act: 7.6254. Min Act: -0.1700
Data Index: 3199436 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9379. Min Range: -7.9379
Max Act: 7.6566. Min Act: -0.1700
Data Index: 5067521 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9379. Min Range: -7.9379
Max Act: 7.5629. Min Act: -0.1700
Data Index: 5488169 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9379. Min Range: -7.9379
Max Act: 7.5629. Min Act: -0.1700
Data Index: 875069 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9379. Min Range: -7.9379
Max Act: 7.4379. Min Act: -0.1700
Data Index: 204738 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9379. Min Range: -7.9379
Max Act: 7.5004. Min Act: -0.1700
Data Index: 4477419 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9379. Min Range: -7.9379
Max Act: 7.4691. Min Act: -0.1700
Data Index: 8003121 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9379. Min Range: -7.9379
Max Act: 7.4379. Min Act: -0.1700
Data Index: 8382034 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9379. Min Range: -7.9379
Max Act: 7.4066. Min Act: -0.1700
Data Index: 1929125 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9379. Min Range: -7.9379
Max Act: 7.3754. Min Act: -0.1700
Data Index: 3705033 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9379. Min Range: -7.9379
Max Act: 7.4066. Min Act: -0.1700
Data Index: 3936367 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9379. Min Range: -7.9379
Max Act: 7.3441. Min Act: -0.1700
Data Index: 6776947 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9379. Min Range: -7.9379
Max Act: 7.2816. Min Act: -0.1700
Data Index: 3652835 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #19