Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 217 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1282. Min Range: -4.1282
Max Act: 4.1282. Min Act: -0.1700
Data Index: 6939758 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1282. Min Range: -4.1282
Max Act: 4.1282. Min Act: -0.1700
Data Index: 4605142 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1282. Min Range: -4.1282
Max Act: 3.9719. Min Act: -0.1700
Data Index: 1794121 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1282. Min Range: -4.1282
Max Act: 3.9719. Min Act: -0.1700
Data Index: 4811138 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1282. Min Range: -4.1282
Max Act: 3.9406. Min Act: -0.1700
Data Index: 2545368 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1282. Min Range: -4.1282
Max Act: 3.9093. Min Act: -0.1700
Data Index: 7270243 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1282. Min Range: -4.1282
Max Act: 3.8781. Min Act: -0.1700
Data Index: 6621496 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1282. Min Range: -4.1282
Max Act: 3.8468. Min Act: -0.1700
Data Index: 3335190 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1282. Min Range: -4.1282
Max Act: 3.8468. Min Act: -0.1700
Data Index: 1354010 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1282. Min Range: -4.1282
Max Act: 3.8155. Min Act: -0.1700
Data Index: 2682045 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1282. Min Range: -4.1282
Max Act: 3.8155. Min Act: -0.1700
Data Index: 1144209 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1282. Min Range: -4.1282
Max Act: 3.7843. Min Act: -0.1700
Data Index: 4482378 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1282. Min Range: -4.1282
Max Act: 3.7843. Min Act: -0.1700
Data Index: 323344 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1282. Min Range: -4.1282
Max Act: 3.7530. Min Act: -0.1700
Data Index: 27418 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1282. Min Range: -4.1282
Max Act: 3.7217. Min Act: -0.1700
Data Index: 7564225 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1282. Min Range: -4.1282
Max Act: 3.7217. Min Act: -0.1700
Data Index: 819430 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1282. Min Range: -4.1282
Max Act: 3.7217. Min Act: -0.1700
Data Index: 7109581 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1282. Min Range: -4.1282
Max Act: 3.7217. Min Act: -0.1700
Data Index: 5418806 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1282. Min Range: -4.1282
Max Act: 3.7530. Min Act: -0.1700
Data Index: 5664427 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1282. Min Range: -4.1282
Max Act: 3.7217. Min Act: -0.1700
Data Index: 74133 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19