Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5782 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7469. Min Range: -7.7469
Max Act: 7.7469. Min Act: -0.1700
Data Index: 4828035 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7469. Min Range: -7.7469
Max Act: 7.5282. Min Act: -0.1700
Data Index: 8079945 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7469. Min Range: -7.7469
Max Act: 7.4032. Min Act: -0.1700
Data Index: 1540499 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7469. Min Range: -7.7469
Max Act: 7.3407. Min Act: -0.1700
Data Index: 1443969 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7469. Min Range: -7.7469
Max Act: 7.2782. Min Act: -0.1700
Data Index: 6679017 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7469. Min Range: -7.7469
Max Act: 7.2782. Min Act: -0.1700
Data Index: 344288 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7469. Min Range: -7.7469
Max Act: 7.1844. Min Act: -0.1700
Data Index: 6820484 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7469. Min Range: -7.7469
Max Act: 7.0907. Min Act: -0.1700
Data Index: 8709790 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7469. Min Range: -7.7469
Max Act: 7.1219. Min Act: -0.1700
Data Index: 8116643 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7469. Min Range: -7.7469
Max Act: 7.0907. Min Act: -0.1700
Data Index: 7983697 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7469. Min Range: -7.7469
Max Act: 7.0907. Min Act: -0.1700
Data Index: 4070466 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7469. Min Range: -7.7469
Max Act: 7.0907. Min Act: -0.1700
Data Index: 3948031 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7469. Min Range: -7.7469
Max Act: 7.0594. Min Act: -0.1700
Data Index: 2043493 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7469. Min Range: -7.7469
Max Act: 7.0907. Min Act: -0.1700
Data Index: 3147000 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7469. Min Range: -7.7469
Max Act: 7.0594. Min Act: -0.1700
Data Index: 8571059 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7469. Min Range: -7.7469
Max Act: 7.0907. Min Act: -0.1700
Data Index: 2266854 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7469. Min Range: -7.7469
Max Act: 7.0282. Min Act: -0.1700
Data Index: 7529860 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7469. Min Range: -7.7469
Max Act: 6.9657. Min Act: -0.1700
Data Index: 5011969 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7469. Min Range: -7.7469
Max Act: 6.9969. Min Act: -0.1700
Data Index: 1802048 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7469. Min Range: -7.7469
Max Act: 7.0282. Min Act: -0.1700
Data Index: 8679756 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19