Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 859 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7443. Min Range: -4.7443
Max Act: 4.7443. Min Act: -0.1700
Data Index: 1161677 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7443. Min Range: -4.7443
Max Act: 4.6193. Min Act: -0.1700
Data Index: 1210723 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7443. Min Range: -4.7443
Max Act: 4.6193. Min Act: -0.1700
Data Index: 629647 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7443. Min Range: -4.7443
Max Act: 4.5880. Min Act: -0.1700
Data Index: 2598135 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7443. Min Range: -4.7443
Max Act: 4.5880. Min Act: -0.1700
Data Index: 1633734 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7443. Min Range: -4.7443
Max Act: 4.6505. Min Act: -0.1700
Data Index: 8343379 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7443. Min Range: -4.7443
Max Act: 4.5880. Min Act: -0.1700
Data Index: 4087776 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7443. Min Range: -4.7443
Max Act: 4.5568. Min Act: -0.1700
Data Index: 7211002 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7443. Min Range: -4.7443
Max Act: 4.5568. Min Act: -0.1700
Data Index: 993407 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7443. Min Range: -4.7443
Max Act: 4.5568. Min Act: -0.1700
Data Index: 1161675 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7443. Min Range: -4.7443
Max Act: 4.4943. Min Act: -0.1700
Data Index: 3393386 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7443. Min Range: -4.7443
Max Act: 4.4630. Min Act: -0.1700
Data Index: 620865 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7443. Min Range: -4.7443
Max Act: 4.4318. Min Act: -0.1700
Data Index: 3893628 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7443. Min Range: -4.7443
Max Act: 4.4318. Min Act: -0.1700
Data Index: 2398532 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7443. Min Range: -4.7443
Max Act: 4.4005. Min Act: -0.1700
Data Index: 5639968 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7443. Min Range: -4.7443
Max Act: 4.3693. Min Act: -0.1700
Data Index: 1161674 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7443. Min Range: -4.7443
Max Act: 4.4005. Min Act: -0.1700
Data Index: 4216912 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7443. Min Range: -4.7443
Max Act: 4.4005. Min Act: -0.1700
Data Index: 1290944 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7443. Min Range: -4.7443
Max Act: 4.3380. Min Act: -0.1700
Data Index: 1161676 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7443. Min Range: -4.7443
Max Act: 4.3380. Min Act: -0.1700
Data Index: 3829276 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19