Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1853 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3678. Min Range: -3.3678
Max Act: 3.3521. Min Act: -0.1700
Data Index: 4230926 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3678. Min Range: -3.3678
Max Act: 3.3678. Min Act: -0.1700
Data Index: 1838891 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3678. Min Range: -3.3678
Max Act: 3.3678. Min Act: -0.1700
Data Index: 1488553 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3678. Min Range: -3.3678
Max Act: 3.3364. Min Act: -0.1700
Data Index: 1223596 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3678. Min Range: -3.3678
Max Act: 3.3050. Min Act: -0.1700
Data Index: 3710576 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3678. Min Range: -3.3678
Max Act: 3.3207. Min Act: -0.1700
Data Index: 3619246 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3678. Min Range: -3.3678
Max Act: 3.2893. Min Act: -0.1700
Data Index: 5826909 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3678. Min Range: -3.3678
Max Act: 3.3050. Min Act: -0.1700
Data Index: 6807794 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3678. Min Range: -3.3678
Max Act: 3.2893. Min Act: -0.1700
Data Index: 1216300 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3678. Min Range: -3.3678
Max Act: 3.2579. Min Act: -0.1700
Data Index: 7243998 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3678. Min Range: -3.3678
Max Act: 3.2893. Min Act: -0.1700
Data Index: 789583 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3678. Min Range: -3.3678
Max Act: 3.2736. Min Act: -0.1700
Data Index: 1948843 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3678. Min Range: -3.3678
Max Act: 3.2579. Min Act: -0.1700
Data Index: 6792767 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3678. Min Range: -3.3678
Max Act: 3.2422. Min Act: -0.1700
Data Index: 4094491 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3678. Min Range: -3.3678
Max Act: 3.2422. Min Act: -0.1700
Data Index: 1790149 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3678. Min Range: -3.3678
Max Act: 3.2422. Min Act: -0.1700
Data Index: 3366879 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3678. Min Range: -3.3678
Max Act: 3.2265. Min Act: -0.1700
Data Index: 3241731 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3678. Min Range: -3.3678
Max Act: 3.2265. Min Act: -0.1700
Data Index: 1718717 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3678. Min Range: -3.3678
Max Act: 3.2108. Min Act: -0.1700
Data Index: 3337445 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3678. Min Range: -3.3678
Max Act: 3.2265. Min Act: -0.1700
Data Index: 3414316 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19