Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4390 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0469. Min Range: -8.0469
Max Act: 8.0469. Min Act: -0.1700
Data Index: 2856453 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0469. Min Range: -8.0469
Max Act: 7.6094. Min Act: -0.1700
Data Index: 812345 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0469. Min Range: -8.0469
Max Act: 7.5781. Min Act: -0.1700
Data Index: 5791658 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0469. Min Range: -8.0469
Max Act: 7.3594. Min Act: -0.1700
Data Index: 3059403 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0469. Min Range: -8.0469
Max Act: 7.3594. Min Act: -0.1700
Data Index: 6209703 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0469. Min Range: -8.0469
Max Act: 7.3594. Min Act: -0.1700
Data Index: 2422345 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0469. Min Range: -8.0469
Max Act: 7.3281. Min Act: -0.1700
Data Index: 4362326 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0469. Min Range: -8.0469
Max Act: 7.2656. Min Act: -0.1700
Data Index: 1277541 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0469. Min Range: -8.0469
Max Act: 7.2656. Min Act: -0.1700
Data Index: 6825450 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0469. Min Range: -8.0469
Max Act: 7.2656. Min Act: -0.1700
Data Index: 7756867 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0469. Min Range: -8.0469
Max Act: 7.2031. Min Act: -0.1700
Data Index: 6387962 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0469. Min Range: -8.0469
Max Act: 7.2031. Min Act: -0.1700
Data Index: 6209705 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0469. Min Range: -8.0469
Max Act: 7.1719. Min Act: -0.1700
Data Index: 8047676 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0469. Min Range: -8.0469
Max Act: 7.1719. Min Act: -0.1700
Data Index: 8722308 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0469. Min Range: -8.0469
Max Act: 7.1719. Min Act: -0.1700
Data Index: 4946981 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0469. Min Range: -8.0469
Max Act: 7.2031. Min Act: -0.1700
Data Index: 2540630 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0469. Min Range: -8.0469
Max Act: 7.1719. Min Act: -0.1700
Data Index: 4749699 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0469. Min Range: -8.0469
Max Act: 7.1719. Min Act: -0.1700
Data Index: 3411382 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0469. Min Range: -8.0469
Max Act: 7.1719. Min Act: -0.1700
Data Index: 1686202 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0469. Min Range: -8.0469
Max Act: 7.1406. Min Act: -0.1700
Data Index: 4149049 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19