Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2759 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6447. Min Range: -2.6447
Max Act: 2.6447. Min Act: -0.1700
Data Index: 3217016 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6447. Min Range: -2.6447
Max Act: 2.5481. Min Act: -0.1700
Data Index: 2650262 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6447. Min Range: -2.6447
Max Act: 2.5481. Min Act: -0.1700
Data Index: 6151224 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6447. Min Range: -2.6447
Max Act: 2.5319. Min Act: -0.1700
Data Index: 5661758 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6447. Min Range: -2.6447
Max Act: 2.5481. Min Act: -0.1700
Data Index: 3914369 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6447. Min Range: -2.6447
Max Act: 2.5158. Min Act: -0.1700
Data Index: 7398086 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6447. Min Range: -2.6447
Max Act: 2.5158. Min Act: -0.1700
Data Index: 2380190 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6447. Min Range: -2.6447
Max Act: 2.4996. Min Act: -0.1700
Data Index: 5649158 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6447. Min Range: -2.6447
Max Act: 2.4834. Min Act: -0.1700
Data Index: 8275421 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6447. Min Range: -2.6447
Max Act: 2.4671. Min Act: -0.1700
Data Index: 4275409 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6447. Min Range: -2.6447
Max Act: 2.4671. Min Act: -0.1700
Data Index: 1529717 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6447. Min Range: -2.6447
Max Act: 2.4509. Min Act: -0.1700
Data Index: 7954001 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6447. Min Range: -2.6447
Max Act: 2.4509. Min Act: -0.1700
Data Index: 69407 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6447. Min Range: -2.6447
Max Act: 2.4509. Min Act: -0.1700
Data Index: 7928075 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6447. Min Range: -2.6447
Max Act: 2.4509. Min Act: -0.1700
Data Index: 2941251 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6447. Min Range: -2.6447
Max Act: 2.4509. Min Act: -0.1700
Data Index: 2285810 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6447. Min Range: -2.6447
Max Act: 2.4346. Min Act: -0.1700
Data Index: 8073870 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6447. Min Range: -2.6447
Max Act: 2.4346. Min Act: -0.1700
Data Index: 8521352 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6447. Min Range: -2.6447
Max Act: 2.4346. Min Act: -0.1700
Data Index: 2301862 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6447. Min Range: -2.6447
Max Act: 2.4346. Min Act: -0.1700
Data Index: 986407 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19