Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 886 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9132. Min Range: -5.9132
Max Act: 5.9132. Min Act: -0.1700
Data Index: 6909960 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9132. Min Range: -5.9132
Max Act: 5.9132. Min Act: -0.1700
Data Index: 1179116 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9132. Min Range: -5.9132
Max Act: 5.9132. Min Act: -0.1700
Data Index: 8507603 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9132. Min Range: -5.9132
Max Act: 5.8195. Min Act: -0.1700
Data Index: 6486124 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9132. Min Range: -5.9132
Max Act: 5.6945. Min Act: -0.1700
Data Index: 4794340 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9132. Min Range: -5.9132
Max Act: 5.6632. Min Act: -0.1700
Data Index: 6384354 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9132. Min Range: -5.9132
Max Act: 5.6632. Min Act: -0.1700
Data Index: 3555111 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9132. Min Range: -5.9132
Max Act: 5.5695. Min Act: -0.1700
Data Index: 4071523 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9132. Min Range: -5.9132
Max Act: 5.5382. Min Act: -0.1700
Data Index: 5597394 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9132. Min Range: -5.9132
Max Act: 5.6007. Min Act: -0.1700
Data Index: 2348081 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9132. Min Range: -5.9132
Max Act: 5.5382. Min Act: -0.1700
Data Index: 4973858 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9132. Min Range: -5.9132
Max Act: 5.5070. Min Act: -0.1700
Data Index: 3504495 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9132. Min Range: -5.9132
Max Act: 5.5382. Min Act: -0.1700
Data Index: 3563116 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9132. Min Range: -5.9132
Max Act: 5.5070. Min Act: -0.1700
Data Index: 4531059 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9132. Min Range: -5.9132
Max Act: 5.4757. Min Act: -0.1700
Data Index: 6609204 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9132. Min Range: -5.9132
Max Act: 5.4757. Min Act: -0.1700
Data Index: 4071521 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9132. Min Range: -5.9132
Max Act: 5.4757. Min Act: -0.1700
Data Index: 1071761 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9132. Min Range: -5.9132
Max Act: 5.4445. Min Act: -0.1700
Data Index: 5350690 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9132. Min Range: -5.9132
Max Act: 5.4445. Min Act: -0.1700
Data Index: 5622560 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9132. Min Range: -5.9132
Max Act: 5.4445. Min Act: -0.1700
Data Index: 8452278 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19