Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1197 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9926. Min Range: -3.9926
Max Act: 3.9926. Min Act: -0.1700
Data Index: 53587 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9926. Min Range: -3.9926
Max Act: 3.9144. Min Act: -0.1700
Data Index: 6072954 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9926. Min Range: -3.9926
Max Act: 3.9144. Min Act: -0.1700
Data Index: 2347914 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9926. Min Range: -3.9926
Max Act: 3.8675. Min Act: -0.1700
Data Index: 1277456 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9926. Min Range: -3.9926
Max Act: 3.8519. Min Act: -0.1700
Data Index: 1531012 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9926. Min Range: -3.9926
Max Act: 3.8050. Min Act: -0.1700
Data Index: 8056717 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9926. Min Range: -3.9926
Max Act: 3.7737. Min Act: -0.1700
Data Index: 402999 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9926. Min Range: -3.9926
Max Act: 3.7268. Min Act: -0.1700
Data Index: 3833496 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9926. Min Range: -3.9926
Max Act: 3.7111. Min Act: -0.1700
Data Index: 5521624 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9926. Min Range: -3.9926
Max Act: 3.6798. Min Act: -0.1700
Data Index: 7522111 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9926. Min Range: -3.9926
Max Act: 3.6798. Min Act: -0.1700
Data Index: 6939160 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9926. Min Range: -3.9926
Max Act: 3.6798. Min Act: -0.1700
Data Index: 2642376 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9926. Min Range: -3.9926
Max Act: 3.6642. Min Act: -0.1700
Data Index: 2562686 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9926. Min Range: -3.9926
Max Act: 3.6642. Min Act: -0.1700
Data Index: 7428778 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9926. Min Range: -3.9926
Max Act: 3.6172. Min Act: -0.1700
Data Index: 7527650 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9926. Min Range: -3.9926
Max Act: 3.6172. Min Act: -0.1700
Data Index: 488228 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9926. Min Range: -3.9926
Max Act: 3.6172. Min Act: -0.1700
Data Index: 165779 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9926. Min Range: -3.9926
Max Act: 3.6016. Min Act: -0.1700
Data Index: 7796836 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9926. Min Range: -3.9926
Max Act: 3.5859. Min Act: -0.1700
Data Index: 3729585 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9926. Min Range: -3.9926
Max Act: 3.5703. Min Act: -0.1700
Data Index: 2647920 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19