Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2002 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.9566. Min Act: -0.1700
Data Index: 7539943 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.9253. Min Act: -0.1700
Data Index: 7627861 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.8941. Min Act: -0.1700
Data Index: 8745524 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.8628. Min Act: -0.1700
Data Index: 4974488 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.8628. Min Act: -0.1700
Data Index: 7247925 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.8003. Min Act: -0.1700
Data Index: 4347228 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.7691. Min Act: -0.1700
Data Index: 7689257 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.7691. Min Act: -0.1700
Data Index: 5239294 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.7378. Min Act: -0.1700
Data Index: 7247924 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.7691. Min Act: -0.1700
Data Index: 6452094 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.7066. Min Act: -0.1700
Data Index: 4326102 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.7378. Min Act: -0.1700
Data Index: 139074 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.7066. Min Act: -0.1700
Data Index: 3541849 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.7378. Min Act: -0.1700
Data Index: 789857 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.7066. Min Act: -0.1700
Data Index: 5229050 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.7066. Min Act: -0.1700
Data Index: 802667 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.7378. Min Act: -0.1700
Data Index: 3887334 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.7378. Min Act: -0.1700
Data Index: 1404288 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.7378. Min Act: -0.1700
Data Index: 5380468 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.7378. Min Act: -0.1700
Data Index: 885861 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19