Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1814 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.9913. Min Act: -0.1700
Data Index: 4462807 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.6786. Min Act: -0.1700
Data Index: 4768851 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.5377. Min Act: -0.1700
Data Index: 4939496 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.5064. Min Act: -0.1700
Data Index: 4230671 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.4751. Min Act: -0.1700
Data Index: 7751527 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.4594. Min Act: -0.1700
Data Index: 4629893 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.4751. Min Act: -0.1700
Data Index: 4535257 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.4437. Min Act: -0.1700
Data Index: 6611474 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.4124. Min Act: -0.1700
Data Index: 6029433 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.3967. Min Act: -0.1700
Data Index: 3604540 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.3967. Min Act: -0.1700
Data Index: 2624915 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.3967. Min Act: -0.1700
Data Index: 1171520 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.3810. Min Act: -0.1700
Data Index: 175423 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.3967. Min Act: -0.1700
Data Index: 8326979 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.3653. Min Act: -0.1700
Data Index: 6462094 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.3653. Min Act: -0.1700
Data Index: 5644839 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.3496. Min Act: -0.1700
Data Index: 8682862 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.3496. Min Act: -0.1700
Data Index: 4341345 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.3340. Min Act: -0.1700
Data Index: 6570075 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.3496. Min Act: -0.1700
Data Index: 6625378 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19