Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5630 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0544. Min Range: -5.0544
Max Act: 5.0544. Min Act: -0.1700
Data Index: 1900587 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0544. Min Range: -5.0544
Max Act: 4.9607. Min Act: -0.1700
Data Index: 2593756 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0544. Min Range: -5.0544
Max Act: 4.9294. Min Act: -0.1700
Data Index: 792927 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0544. Min Range: -5.0544
Max Act: 4.8669. Min Act: -0.1700
Data Index: 4352435 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0544. Min Range: -5.0544
Max Act: 4.8669. Min Act: -0.1700
Data Index: 8765178 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0544. Min Range: -5.0544
Max Act: 4.8669. Min Act: -0.1700
Data Index: 3572732 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0544. Min Range: -5.0544
Max Act: 4.8044. Min Act: -0.1700
Data Index: 4046374 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0544. Min Range: -5.0544
Max Act: 4.7419. Min Act: -0.1700
Data Index: 6068967 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0544. Min Range: -5.0544
Max Act: 4.7419. Min Act: -0.1700
Data Index: 7398863 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0544. Min Range: -5.0544
Max Act: 4.7107. Min Act: -0.1700
Data Index: 1754083 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0544. Min Range: -5.0544
Max Act: 4.6794. Min Act: -0.1700
Data Index: 8627313 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0544. Min Range: -5.0544
Max Act: 4.7107. Min Act: -0.1700
Data Index: 5313387 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0544. Min Range: -5.0544
Max Act: 4.7107. Min Act: -0.1700
Data Index: 4471278 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0544. Min Range: -5.0544
Max Act: 4.7107. Min Act: -0.1700
Data Index: 6745053 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0544. Min Range: -5.0544
Max Act: 4.6794. Min Act: -0.1700
Data Index: 4058824 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0544. Min Range: -5.0544
Max Act: 4.6794. Min Act: -0.1700
Data Index: 6211513 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0544. Min Range: -5.0544
Max Act: 4.6794. Min Act: -0.1700
Data Index: 1337482 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0544. Min Range: -5.0544
Max Act: 4.6794. Min Act: -0.1700
Data Index: 3703737 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0544. Min Range: -5.0544
Max Act: 4.6482. Min Act: -0.1700
Data Index: 4455974 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0544. Min Range: -5.0544
Max Act: 4.6482. Min Act: -0.1700
Data Index: 3249013 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19