Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3286 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9148. Min Range: -10.9148
Max Act: 10.9148. Min Act: -0.1700
Data Index: 8408774 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9148. Min Range: -10.9148
Max Act: 10.6023. Min Act: -0.1700
Data Index: 1064213 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9148. Min Range: -10.9148
Max Act: 10.0398. Min Act: -0.1700
Data Index: 5138349 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9148. Min Range: -10.9148
Max Act: 9.9773. Min Act: -0.1700
Data Index: 2013704 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9148. Min Range: -10.9148
Max Act: 9.8523. Min Act: -0.1700
Data Index: 3244564 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9148. Min Range: -10.9148
Max Act: 9.7273. Min Act: -0.1700
Data Index: 458242 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9148. Min Range: -10.9148
Max Act: 9.6648. Min Act: -0.1700
Data Index: 474164 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9148. Min Range: -10.9148
Max Act: 9.6648. Min Act: -0.1700
Data Index: 3975448 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9148. Min Range: -10.9148
Max Act: 9.5398. Min Act: -0.1700
Data Index: 6970134 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9148. Min Range: -10.9148
Max Act: 9.6023. Min Act: -0.1700
Data Index: 2970785 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9148. Min Range: -10.9148
Max Act: 9.6023. Min Act: -0.1700
Data Index: 2290630 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9148. Min Range: -10.9148
Max Act: 9.5398. Min Act: -0.1700
Data Index: 5183916 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9148. Min Range: -10.9148
Max Act: 9.5398. Min Act: -0.1700
Data Index: 3614342 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9148. Min Range: -10.9148
Max Act: 9.5398. Min Act: -0.1700
Data Index: 8612848 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9148. Min Range: -10.9148
Max Act: 9.5398. Min Act: -0.1700
Data Index: 1218467 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9148. Min Range: -10.9148
Max Act: 9.5398. Min Act: -0.1700
Data Index: 3283780 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9148. Min Range: -10.9148
Max Act: 9.5398. Min Act: -0.1700
Data Index: 3840489 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9148. Min Range: -10.9148
Max Act: 9.5398. Min Act: -0.1700
Data Index: 4772057 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9148. Min Range: -10.9148
Max Act: 9.5398. Min Act: -0.1700
Data Index: 6064419 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9148. Min Range: -10.9148
Max Act: 9.4773. Min Act: -0.1700
Data Index: 1793053 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19