Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2658 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5123. Min Range: -7.5123
Max Act: 7.5123. Min Act: -0.1700
Data Index: 3419338 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5123. Min Range: -7.5123
Max Act: 7.3560. Min Act: -0.1700
Data Index: 3358439 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5123. Min Range: -7.5123
Max Act: 7.2623. Min Act: -0.1700
Data Index: 3741663 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5123. Min Range: -7.5123
Max Act: 7.1060. Min Act: -0.1700
Data Index: 7739468 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5123. Min Range: -7.5123
Max Act: 7.0748. Min Act: -0.1700
Data Index: 3419336 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5123. Min Range: -7.5123
Max Act: 6.9810. Min Act: -0.1700
Data Index: 3816313 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5123. Min Range: -7.5123
Max Act: 6.9810. Min Act: -0.1700
Data Index: 6103115 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5123. Min Range: -7.5123
Max Act: 6.9498. Min Act: -0.1700
Data Index: 2124025 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5123. Min Range: -7.5123
Max Act: 6.8873. Min Act: -0.1700
Data Index: 4439544 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5123. Min Range: -7.5123
Max Act: 6.7935. Min Act: -0.1700
Data Index: 2236708 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5123. Min Range: -7.5123
Max Act: 6.8248. Min Act: -0.1700
Data Index: 7021603 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5123. Min Range: -7.5123
Max Act: 6.8248. Min Act: -0.1700
Data Index: 4099717 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5123. Min Range: -7.5123
Max Act: 6.7935. Min Act: -0.1700
Data Index: 7904506 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5123. Min Range: -7.5123
Max Act: 6.7935. Min Act: -0.1700
Data Index: 7702634 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5123. Min Range: -7.5123
Max Act: 6.7935. Min Act: -0.1700
Data Index: 8315226 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5123. Min Range: -7.5123
Max Act: 6.7623. Min Act: -0.1700
Data Index: 1106679 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5123. Min Range: -7.5123
Max Act: 6.7623. Min Act: -0.1700
Data Index: 3425851 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5123. Min Range: -7.5123
Max Act: 6.7623. Min Act: -0.1700
Data Index: 4864717 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5123. Min Range: -7.5123
Max Act: 6.7623. Min Act: -0.1700
Data Index: 2807252 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5123. Min Range: -7.5123
Max Act: 6.7310. Min Act: -0.1700
Data Index: 2117818 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19