Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3108 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9108. Min Range: -5.9108
Max Act: 5.9108. Min Act: -0.1700
Data Index: 609089 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9108. Min Range: -5.9108
Max Act: 5.6295. Min Act: -0.1700
Data Index: 4227605 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9108. Min Range: -5.9108
Max Act: 5.6295. Min Act: -0.1700
Data Index: 4890277 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9108. Min Range: -5.9108
Max Act: 5.5670. Min Act: -0.1700
Data Index: 3000520 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9108. Min Range: -5.9108
Max Act: 5.5670. Min Act: -0.1700
Data Index: 1147464 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9108. Min Range: -5.9108
Max Act: 5.5358. Min Act: -0.1700
Data Index: 2180440 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9108. Min Range: -5.9108
Max Act: 5.5045. Min Act: -0.1700
Data Index: 7691258 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9108. Min Range: -5.9108
Max Act: 5.4420. Min Act: -0.1700
Data Index: 1201645 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9108. Min Range: -5.9108
Max Act: 5.4108. Min Act: -0.1700
Data Index: 7865958 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9108. Min Range: -5.9108
Max Act: 5.3795. Min Act: -0.1700
Data Index: 8527039 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9108. Min Range: -5.9108
Max Act: 5.3170. Min Act: -0.1700
Data Index: 5106385 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9108. Min Range: -5.9108
Max Act: 5.3483. Min Act: -0.1700
Data Index: 7963801 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9108. Min Range: -5.9108
Max Act: 5.3170. Min Act: -0.1700
Data Index: 768723 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9108. Min Range: -5.9108
Max Act: 5.3170. Min Act: -0.1700
Data Index: 438576 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9108. Min Range: -5.9108
Max Act: 5.2858. Min Act: -0.1700
Data Index: 2656460 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9108. Min Range: -5.9108
Max Act: 5.2545. Min Act: -0.1700
Data Index: 6174429 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9108. Min Range: -5.9108
Max Act: 5.2545. Min Act: -0.1700
Data Index: 5151560 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9108. Min Range: -5.9108
Max Act: 5.2233. Min Act: -0.1700
Data Index: 5879763 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9108. Min Range: -5.9108
Max Act: 5.2233. Min Act: -0.1700
Data Index: 2795548 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9108. Min Range: -5.9108
Max Act: 5.2233. Min Act: -0.1700
Data Index: 8730187 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19