Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1567 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4688. Min Range: -7.4688
Max Act: 7.4688. Min Act: -0.1700
Data Index: 5211475 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4688. Min Range: -7.4688
Max Act: 7.4688. Min Act: -0.1700
Data Index: 3383727 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4688. Min Range: -7.4688
Max Act: 7.3750. Min Act: -0.1700
Data Index: 4604725 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4688. Min Range: -7.4688
Max Act: 7.3438. Min Act: -0.1700
Data Index: 7268727 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4688. Min Range: -7.4688
Max Act: 7.2500. Min Act: -0.1700
Data Index: 2383577 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4688. Min Range: -7.4688
Max Act: 7.1250. Min Act: -0.1700
Data Index: 4251124 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4688. Min Range: -7.4688
Max Act: 7.0938. Min Act: -0.1700
Data Index: 248718 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4688. Min Range: -7.4688
Max Act: 7.0313. Min Act: -0.1700
Data Index: 7449150 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4688. Min Range: -7.4688
Max Act: 6.9688. Min Act: -0.1700
Data Index: 712101 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4688. Min Range: -7.4688
Max Act: 7.0000. Min Act: -0.1700
Data Index: 5859173 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4688. Min Range: -7.4688
Max Act: 6.9688. Min Act: -0.1700
Data Index: 611377 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4688. Min Range: -7.4688
Max Act: 6.9375. Min Act: -0.1700
Data Index: 2748742 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4688. Min Range: -7.4688
Max Act: 7.0000. Min Act: -0.1700
Data Index: 5805801 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4688. Min Range: -7.4688
Max Act: 6.9688. Min Act: -0.1700
Data Index: 4354937 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4688. Min Range: -7.4688
Max Act: 6.9375. Min Act: -0.1700
Data Index: 7725381 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4688. Min Range: -7.4688
Max Act: 6.9063. Min Act: -0.1700
Data Index: 7442482 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4688. Min Range: -7.4688
Max Act: 6.9063. Min Act: -0.1700
Data Index: 5694336 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4688. Min Range: -7.4688
Max Act: 6.8750. Min Act: -0.1700
Data Index: 4264248 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4688. Min Range: -7.4688
Max Act: 6.8125. Min Act: -0.1700
Data Index: 3980042 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4688. Min Range: -7.4688
Max Act: 6.8125. Min Act: -0.1700
Data Index: 4528029 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19