Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4064 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6325. Min Range: -6.6325
Max Act: 6.6325. Min Act: -0.1700
Data Index: 1510367 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6325. Min Range: -6.6325
Max Act: 6.5388. Min Act: -0.1700
Data Index: 2596485 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6325. Min Range: -6.6325
Max Act: 6.4450. Min Act: -0.1700
Data Index: 7585260 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6325. Min Range: -6.6325
Max Act: 6.3513. Min Act: -0.1700
Data Index: 3047712 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6325. Min Range: -6.6325
Max Act: 6.3513. Min Act: -0.1700
Data Index: 616762 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6325. Min Range: -6.6325
Max Act: 6.3200. Min Act: -0.1700
Data Index: 3370233 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6325. Min Range: -6.6325
Max Act: 6.3200. Min Act: -0.1700
Data Index: 112329 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6325. Min Range: -6.6325
Max Act: 6.2888. Min Act: -0.1700
Data Index: 4486991 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6325. Min Range: -6.6325
Max Act: 6.2888. Min Act: -0.1700
Data Index: 3880001 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6325. Min Range: -6.6325
Max Act: 6.2575. Min Act: -0.1700
Data Index: 4244709 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6325. Min Range: -6.6325
Max Act: 6.2263. Min Act: -0.1700
Data Index: 3812873 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6325. Min Range: -6.6325
Max Act: 6.2263. Min Act: -0.1700
Data Index: 5632822 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6325. Min Range: -6.6325
Max Act: 6.1950. Min Act: -0.1700
Data Index: 5695388 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6325. Min Range: -6.6325
Max Act: 6.1325. Min Act: -0.1700
Data Index: 6077850 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6325. Min Range: -6.6325
Max Act: 6.1325. Min Act: -0.1700
Data Index: 6342752 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6325. Min Range: -6.6325
Max Act: 6.1325. Min Act: -0.1700
Data Index: 8251944 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6325. Min Range: -6.6325
Max Act: 6.0700. Min Act: -0.1700
Data Index: 4244708 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6325. Min Range: -6.6325
Max Act: 6.0700. Min Act: -0.1700
Data Index: 8088549 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6325. Min Range: -6.6325
Max Act: 6.1013. Min Act: -0.1700
Data Index: 4114612 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6325. Min Range: -6.6325
Max Act: 6.0700. Min Act: -0.1700
Data Index: 3176540 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19