Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6046 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9264. Min Range: -5.9264
Max Act: 5.9264. Min Act: -0.1700
Data Index: 8657590 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9264. Min Range: -5.9264
Max Act: 5.8327. Min Act: -0.1700
Data Index: 8503352 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9264. Min Range: -5.9264
Max Act: 5.7702. Min Act: -0.1700
Data Index: 8345696 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9264. Min Range: -5.9264
Max Act: 5.7077. Min Act: -0.1700
Data Index: 8434355 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9264. Min Range: -5.9264
Max Act: 5.7077. Min Act: -0.1700
Data Index: 2223165 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9264. Min Range: -5.9264
Max Act: 5.7077. Min Act: -0.1700
Data Index: 454301 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9264. Min Range: -5.9264
Max Act: 5.6764. Min Act: -0.1700
Data Index: 8610616 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9264. Min Range: -5.9264
Max Act: 5.6452. Min Act: -0.1700
Data Index: 4271300 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9264. Min Range: -5.9264
Max Act: 5.6764. Min Act: -0.1700
Data Index: 8092695 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9264. Min Range: -5.9264
Max Act: 5.6452. Min Act: -0.1700
Data Index: 2254783 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9264. Min Range: -5.9264
Max Act: 5.6139. Min Act: -0.1700
Data Index: 94039 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9264. Min Range: -5.9264
Max Act: 5.5827. Min Act: -0.1700
Data Index: 1176437 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9264. Min Range: -5.9264
Max Act: 5.5514. Min Act: -0.1700
Data Index: 4097274 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9264. Min Range: -5.9264
Max Act: 5.5827. Min Act: -0.1700
Data Index: 4335643 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9264. Min Range: -5.9264
Max Act: 5.5202. Min Act: -0.1700
Data Index: 2835189 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9264. Min Range: -5.9264
Max Act: 5.5202. Min Act: -0.1700
Data Index: 1258385 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9264. Min Range: -5.9264
Max Act: 5.5202. Min Act: -0.1700
Data Index: 7868728 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9264. Min Range: -5.9264
Max Act: 5.5202. Min Act: -0.1700
Data Index: 7527700 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9264. Min Range: -5.9264
Max Act: 5.4889. Min Act: -0.1700
Data Index: 2279227 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9264. Min Range: -5.9264
Max Act: 5.4889. Min Act: -0.1700
Data Index: 1238164 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19