Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2573 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1285. Min Range: -5.1285
Max Act: 5.1285. Min Act: -0.1700
Data Index: 2131640 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1285. Min Range: -5.1285
Max Act: 5.0035. Min Act: -0.1700
Data Index: 3081438 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1285. Min Range: -5.1285
Max Act: 4.9722. Min Act: -0.1700
Data Index: 5436715 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1285. Min Range: -5.1285
Max Act: 4.8785. Min Act: -0.1700
Data Index: 5436731 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1285. Min Range: -5.1285
Max Act: 4.8472. Min Act: -0.1700
Data Index: 4648933 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1285. Min Range: -5.1285
Max Act: 4.8160. Min Act: -0.1700
Data Index: 5436717 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1285. Min Range: -5.1285
Max Act: 4.8785. Min Act: -0.1700
Data Index: 3081433 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1285. Min Range: -5.1285
Max Act: 4.8160. Min Act: -0.1700
Data Index: 4648936 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1285. Min Range: -5.1285
Max Act: 4.8160. Min Act: -0.1700
Data Index: 6278633 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1285. Min Range: -5.1285
Max Act: 4.8160. Min Act: -0.1700
Data Index: 3081432 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1285. Min Range: -5.1285
Max Act: 4.8160. Min Act: -0.1700
Data Index: 3081440 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1285. Min Range: -5.1285
Max Act: 4.8160. Min Act: -0.1700
Data Index: 8121715 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1285. Min Range: -5.1285
Max Act: 4.8160. Min Act: -0.1700
Data Index: 4648941 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1285. Min Range: -5.1285
Max Act: 4.7847. Min Act: -0.1700
Data Index: 4648943 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1285. Min Range: -5.1285
Max Act: 4.7847. Min Act: -0.1700
Data Index: 5436720 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1285. Min Range: -5.1285
Max Act: 4.7535. Min Act: -0.1700
Data Index: 4648932 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1285. Min Range: -5.1285
Max Act: 4.7535. Min Act: -0.1700
Data Index: 3081441 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1285. Min Range: -5.1285
Max Act: 4.7222. Min Act: -0.1700
Data Index: 3081436 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1285. Min Range: -5.1285
Max Act: 4.7222. Min Act: -0.1700
Data Index: 5436730 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1285. Min Range: -5.1285
Max Act: 4.7535. Min Act: -0.1700
Data Index: 5436725 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19