Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2426 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5285. Min Range: -3.5285
Max Act: 3.5285. Min Act: -0.1700
Data Index: 7776316 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5285. Min Range: -3.5285
Max Act: 3.4658. Min Act: -0.1700
Data Index: 7163876 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5285. Min Range: -3.5285
Max Act: 3.4971. Min Act: -0.1700
Data Index: 1413758 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5285. Min Range: -3.5285
Max Act: 3.4971. Min Act: -0.1700
Data Index: 6108383 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5285. Min Range: -3.5285
Max Act: 3.4345. Min Act: -0.1700
Data Index: 413207 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5285. Min Range: -3.5285
Max Act: 3.4345. Min Act: -0.1700
Data Index: 7244780 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5285. Min Range: -3.5285
Max Act: 3.4345. Min Act: -0.1700
Data Index: 5155233 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5285. Min Range: -3.5285
Max Act: 3.4345. Min Act: -0.1700
Data Index: 7525561 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5285. Min Range: -3.5285
Max Act: 3.4345. Min Act: -0.1700
Data Index: 961659 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5285. Min Range: -3.5285
Max Act: 3.4345. Min Act: -0.1700
Data Index: 3678077 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5285. Min Range: -3.5285
Max Act: 3.4345. Min Act: -0.1700
Data Index: 3678076 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5285. Min Range: -3.5285
Max Act: 3.4031. Min Act: -0.1700
Data Index: 980295 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5285. Min Range: -3.5285
Max Act: 3.4031. Min Act: -0.1700
Data Index: 2999594 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5285. Min Range: -3.5285
Max Act: 3.4031. Min Act: -0.1700
Data Index: 3002996 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5285. Min Range: -3.5285
Max Act: 3.4031. Min Act: -0.1700
Data Index: 6059940 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5285. Min Range: -3.5285
Max Act: 3.4031. Min Act: -0.1700
Data Index: 3334417 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5285. Min Range: -3.5285
Max Act: 3.4031. Min Act: -0.1700
Data Index: 247796 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5285. Min Range: -3.5285
Max Act: 3.4031. Min Act: -0.1700
Data Index: 6256875 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5285. Min Range: -3.5285
Max Act: 3.4031. Min Act: -0.1700
Data Index: 6535558 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5285. Min Range: -3.5285
Max Act: 3.4031. Min Act: -0.1700
Data Index: 2242985 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19