Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4661 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0229. Min Range: -3.0229
Max Act: 3.0071. Min Act: -0.1700
Data Index: 5673667 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0229. Min Range: -3.0229
Max Act: 3.0229. Min Act: -0.1700
Data Index: 6947826 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0229. Min Range: -3.0229
Max Act: 3.0071. Min Act: -0.1700
Data Index: 235672 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0229. Min Range: -3.0229
Max Act: 3.0071. Min Act: -0.1700
Data Index: 5998478 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0229. Min Range: -3.0229
Max Act: 3.0229. Min Act: -0.1700
Data Index: 2290281 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.9913. Min Act: -0.1700
Data Index: 8266162 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.9755. Min Act: -0.1700
Data Index: 4250853 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.9755. Min Act: -0.1700
Data Index: 3529676 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.9439. Min Act: -0.1700
Data Index: 5902546 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.9597. Min Act: -0.1700
Data Index: 1011570 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.9439. Min Act: -0.1700
Data Index: 2401019 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.9280. Min Act: -0.1700
Data Index: 4776063 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.9280. Min Act: -0.1700
Data Index: 5829286 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.9122. Min Act: -0.1700
Data Index: 6360459 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.9280. Min Act: -0.1700
Data Index: 2588263 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.9122. Min Act: -0.1700
Data Index: 1548618 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.9122. Min Act: -0.1700
Data Index: 551666 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.8963. Min Act: -0.1700
Data Index: 4865334 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.8963. Min Act: -0.1700
Data Index: 3064990 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.9122. Min Act: -0.1700
Data Index: 7983861 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19