Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4131 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1707. Min Range: -8.1707
Max Act: 8.1707. Min Act: -0.1700
Data Index: 1563379 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1707. Min Range: -8.1707
Max Act: 7.8582. Min Act: -0.1700
Data Index: 2823614 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1707. Min Range: -8.1707
Max Act: 7.7957. Min Act: -0.1700
Data Index: 5773756 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1707. Min Range: -8.1707
Max Act: 7.7957. Min Act: -0.1700
Data Index: 3271157 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1707. Min Range: -8.1707
Max Act: 7.7957. Min Act: -0.1700
Data Index: 568201 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1707. Min Range: -8.1707
Max Act: 7.7332. Min Act: -0.1700
Data Index: 2690244 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1707. Min Range: -8.1707
Max Act: 7.6707. Min Act: -0.1700
Data Index: 4167161 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1707. Min Range: -8.1707
Max Act: 7.6707. Min Act: -0.1700
Data Index: 4808555 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1707. Min Range: -8.1707
Max Act: 7.6707. Min Act: -0.1700
Data Index: 5374443 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1707. Min Range: -8.1707
Max Act: 7.6707. Min Act: -0.1700
Data Index: 8600012 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1707. Min Range: -8.1707
Max Act: 7.6707. Min Act: -0.1700
Data Index: 310714 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1707. Min Range: -8.1707
Max Act: 7.6707. Min Act: -0.1700
Data Index: 1497163 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1707. Min Range: -8.1707
Max Act: 7.6082. Min Act: -0.1700
Data Index: 7216148 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1707. Min Range: -8.1707
Max Act: 7.6082. Min Act: -0.1700
Data Index: 331792 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1707. Min Range: -8.1707
Max Act: 7.6082. Min Act: -0.1700
Data Index: 3977338 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1707. Min Range: -8.1707
Max Act: 7.6082. Min Act: -0.1700
Data Index: 3141364 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1707. Min Range: -8.1707
Max Act: 7.6707. Min Act: -0.1700
Data Index: 8383224 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1707. Min Range: -8.1707
Max Act: 7.6082. Min Act: -0.1700
Data Index: 5045546 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1707. Min Range: -8.1707
Max Act: 7.5457. Min Act: -0.1700
Data Index: 5951203 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1707. Min Range: -8.1707
Max Act: 7.5457. Min Act: -0.1700
Data Index: 1557863 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19