Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2256 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3377. Min Range: -7.3377
Max Act: 7.3377. Min Act: -0.1700
Data Index: 7257863 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3377. Min Range: -7.3377
Max Act: 7.3064. Min Act: -0.1700
Data Index: 5116319 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3377. Min Range: -7.3377
Max Act: 6.9002. Min Act: -0.1700
Data Index: 4528858 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3377. Min Range: -7.3377
Max Act: 6.8377. Min Act: -0.1700
Data Index: 590984 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3377. Min Range: -7.3377
Max Act: 6.8064. Min Act: -0.1700
Data Index: 4790384 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3377. Min Range: -7.3377
Max Act: 6.7752. Min Act: -0.1700
Data Index: 2011302 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3377. Min Range: -7.3377
Max Act: 6.8064. Min Act: -0.1700
Data Index: 7230887 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3377. Min Range: -7.3377
Max Act: 6.7439. Min Act: -0.1700
Data Index: 4304661 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3377. Min Range: -7.3377
Max Act: 6.7439. Min Act: -0.1700
Data Index: 7221679 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3377. Min Range: -7.3377
Max Act: 6.7439. Min Act: -0.1700
Data Index: 7790889 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3377. Min Range: -7.3377
Max Act: 6.7439. Min Act: -0.1700
Data Index: 3381528 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3377. Min Range: -7.3377
Max Act: 6.6814. Min Act: -0.1700
Data Index: 4873287 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3377. Min Range: -7.3377
Max Act: 6.6502. Min Act: -0.1700
Data Index: 1698080 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3377. Min Range: -7.3377
Max Act: 6.5877. Min Act: -0.1700
Data Index: 790199 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3377. Min Range: -7.3377
Max Act: 6.5877. Min Act: -0.1700
Data Index: 2996900 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3377. Min Range: -7.3377
Max Act: 6.6189. Min Act: -0.1700
Data Index: 5258798 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3377. Min Range: -7.3377
Max Act: 6.5877. Min Act: -0.1700
Data Index: 788680 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3377. Min Range: -7.3377
Max Act: 6.5877. Min Act: -0.1700
Data Index: 5197527 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3377. Min Range: -7.3377
Max Act: 6.5877. Min Act: -0.1700
Data Index: 7192169 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3377. Min Range: -7.3377
Max Act: 6.6189. Min Act: -0.1700
Data Index: 3098624 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19