Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4815 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3355. Min Range: -6.3355
Max Act: 6.3355. Min Act: -0.1700
Data Index: 1079187 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3355. Min Range: -6.3355
Max Act: 6.3355. Min Act: -0.1700
Data Index: 2187875 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3355. Min Range: -6.3355
Max Act: 6.2730. Min Act: -0.1700
Data Index: 4334835 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3355. Min Range: -6.3355
Max Act: 6.2730. Min Act: -0.1700
Data Index: 4513462 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3355. Min Range: -6.3355
Max Act: 6.2730. Min Act: -0.1700
Data Index: 120776 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3355. Min Range: -6.3355
Max Act: 6.2418. Min Act: -0.1700
Data Index: 3650261 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3355. Min Range: -6.3355
Max Act: 6.1793. Min Act: -0.1700
Data Index: 5881362 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3355. Min Range: -6.3355
Max Act: 6.1793. Min Act: -0.1700
Data Index: 6117413 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3355. Min Range: -6.3355
Max Act: 6.1168. Min Act: -0.1700
Data Index: 3121987 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3355. Min Range: -6.3355
Max Act: 6.0855. Min Act: -0.1700
Data Index: 4435145 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3355. Min Range: -6.3355
Max Act: 6.0230. Min Act: -0.1700
Data Index: 466559 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3355. Min Range: -6.3355
Max Act: 6.0230. Min Act: -0.1700
Data Index: 3775742 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3355. Min Range: -6.3355
Max Act: 6.0230. Min Act: -0.1700
Data Index: 3117198 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3355. Min Range: -6.3355
Max Act: 5.9918. Min Act: -0.1700
Data Index: 8172367 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3355. Min Range: -6.3355
Max Act: 5.9918. Min Act: -0.1700
Data Index: 2994315 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3355. Min Range: -6.3355
Max Act: 5.9918. Min Act: -0.1700
Data Index: 3916140 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3355. Min Range: -6.3355
Max Act: 5.9605. Min Act: -0.1700
Data Index: 2571309 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3355. Min Range: -6.3355
Max Act: 5.9605. Min Act: -0.1700
Data Index: 7777628 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3355. Min Range: -6.3355
Max Act: 5.9293. Min Act: -0.1700
Data Index: 1514781 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3355. Min Range: -6.3355
Max Act: 5.9293. Min Act: -0.1700
Data Index: 3883270 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19