Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2743 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8528. Min Range: -2.8528
Max Act: 2.8528. Min Act: -0.1700
Data Index: 5375878 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8528. Min Range: -2.8528
Max Act: 2.8210. Min Act: -0.1700
Data Index: 6632830 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8528. Min Range: -2.8528
Max Act: 2.8051. Min Act: -0.1700
Data Index: 3619259 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8528. Min Range: -2.8528
Max Act: 2.8210. Min Act: -0.1700
Data Index: 3327601 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8528. Min Range: -2.8528
Max Act: 2.8051. Min Act: -0.1700
Data Index: 539692 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8528. Min Range: -2.8528
Max Act: 2.8051. Min Act: -0.1700
Data Index: 6380210 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8528. Min Range: -2.8528
Max Act: 2.7573. Min Act: -0.1700
Data Index: 2072750 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8528. Min Range: -2.8528
Max Act: 2.7732. Min Act: -0.1700
Data Index: 6668495 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8528. Min Range: -2.8528
Max Act: 2.7573. Min Act: -0.1700
Data Index: 8571332 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8528. Min Range: -2.8528
Max Act: 2.7732. Min Act: -0.1700
Data Index: 2416175 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8528. Min Range: -2.8528
Max Act: 2.7732. Min Act: -0.1700
Data Index: 7944251 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8528. Min Range: -2.8528
Max Act: 2.7253. Min Act: -0.1700
Data Index: 1332190 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8528. Min Range: -2.8528
Max Act: 2.7093. Min Act: -0.1700
Data Index: 4206027 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8528. Min Range: -2.8528
Max Act: 2.7413. Min Act: -0.1700
Data Index: 916824 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8528. Min Range: -2.8528
Max Act: 2.7413. Min Act: -0.1700
Data Index: 1411158 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8528. Min Range: -2.8528
Max Act: 2.7253. Min Act: -0.1700
Data Index: 6479512 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8528. Min Range: -2.8528
Max Act: 2.7413. Min Act: -0.1700
Data Index: 2634905 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8528. Min Range: -2.8528
Max Act: 2.7253. Min Act: -0.1700
Data Index: 16354 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8528. Min Range: -2.8528
Max Act: 2.7253. Min Act: -0.1700
Data Index: 7318497 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8528. Min Range: -2.8528
Max Act: 2.6933. Min Act: -0.1700
Data Index: 1026094 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19