Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1920 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8909. Min Range: -4.8909
Max Act: 4.8909. Min Act: -0.1700
Data Index: 5700709 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8909. Min Range: -4.8909
Max Act: 4.8909. Min Act: -0.1700
Data Index: 6403858 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8909. Min Range: -4.8909
Max Act: 4.8597. Min Act: -0.1700
Data Index: 4878856 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8909. Min Range: -4.8909
Max Act: 4.8597. Min Act: -0.1700
Data Index: 5085386 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8909. Min Range: -4.8909
Max Act: 4.8597. Min Act: -0.1700
Data Index: 3242748 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8909. Min Range: -4.8909
Max Act: 4.8597. Min Act: -0.1700
Data Index: 1116051 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8909. Min Range: -4.8909
Max Act: 4.7972. Min Act: -0.1700
Data Index: 2391800 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8909. Min Range: -4.8909
Max Act: 4.7972. Min Act: -0.1700
Data Index: 6626799 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8909. Min Range: -4.8909
Max Act: 4.7659. Min Act: -0.1700
Data Index: 1423999 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8909. Min Range: -4.8909
Max Act: 4.7659. Min Act: -0.1700
Data Index: 8628229 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8909. Min Range: -4.8909
Max Act: 4.7659. Min Act: -0.1700
Data Index: 7035577 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8909. Min Range: -4.8909
Max Act: 4.7659. Min Act: -0.1700
Data Index: 208223 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8909. Min Range: -4.8909
Max Act: 4.7034. Min Act: -0.1700
Data Index: 1043482 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8909. Min Range: -4.8909
Max Act: 4.7034. Min Act: -0.1700
Data Index: 4483197 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8909. Min Range: -4.8909
Max Act: 4.7034. Min Act: -0.1700
Data Index: 105470 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8909. Min Range: -4.8909
Max Act: 4.7034. Min Act: -0.1700
Data Index: 8058226 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8909. Min Range: -4.8909
Max Act: 4.7034. Min Act: -0.1700
Data Index: 7378945 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8909. Min Range: -4.8909
Max Act: 4.6722. Min Act: -0.1700
Data Index: 5805817 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8909. Min Range: -4.8909
Max Act: 4.6722. Min Act: -0.1700
Data Index: 605818 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8909. Min Range: -4.8909
Max Act: 4.6409. Min Act: -0.1700
Data Index: 3307059 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19