Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3567 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2820. Min Range: -6.2820
Max Act: 6.2820. Min Act: -0.1700
Data Index: 8757668 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2820. Min Range: -6.2820
Max Act: 6.0320. Min Act: -0.1700
Data Index: 3234472 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2820. Min Range: -6.2820
Max Act: 6.0008. Min Act: -0.1700
Data Index: 5888750 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2820. Min Range: -6.2820
Max Act: 5.8758. Min Act: -0.1700
Data Index: 5603256 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2820. Min Range: -6.2820
Max Act: 5.9383. Min Act: -0.1700
Data Index: 5741792 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2820. Min Range: -6.2820
Max Act: 5.8758. Min Act: -0.1700
Data Index: 526813 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2820. Min Range: -6.2820
Max Act: 5.8133. Min Act: -0.1700
Data Index: 6486288 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2820. Min Range: -6.2820
Max Act: 5.7508. Min Act: -0.1700
Data Index: 8292452 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2820. Min Range: -6.2820
Max Act: 5.7195. Min Act: -0.1700
Data Index: 400993 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2820. Min Range: -6.2820
Max Act: 5.7195. Min Act: -0.1700
Data Index: 3672991 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2820. Min Range: -6.2820
Max Act: 5.6883. Min Act: -0.1700
Data Index: 720941 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2820. Min Range: -6.2820
Max Act: 5.6883. Min Act: -0.1700
Data Index: 1609643 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2820. Min Range: -6.2820
Max Act: 5.6570. Min Act: -0.1700
Data Index: 4612746 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2820. Min Range: -6.2820
Max Act: 5.6258. Min Act: -0.1700
Data Index: 5983526 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2820. Min Range: -6.2820
Max Act: 5.6258. Min Act: -0.1700
Data Index: 4189717 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2820. Min Range: -6.2820
Max Act: 5.6258. Min Act: -0.1700
Data Index: 1556672 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2820. Min Range: -6.2820
Max Act: 5.6570. Min Act: -0.1700
Data Index: 6601365 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2820. Min Range: -6.2820
Max Act: 5.6258. Min Act: -0.1700
Data Index: 3030672 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2820. Min Range: -6.2820
Max Act: 5.5945. Min Act: -0.1700
Data Index: 7510461 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2820. Min Range: -6.2820
Max Act: 5.5633. Min Act: -0.1700
Data Index: 705876 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #19