Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3463 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6278. Min Range: -6.6278
Max Act: 6.6278. Min Act: -0.1700
Data Index: 1482624 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6278. Min Range: -6.6278
Max Act: 6.4403. Min Act: -0.1700
Data Index: 2235752 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6278. Min Range: -6.6278
Max Act: 6.3778. Min Act: -0.1700
Data Index: 6523761 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6278. Min Range: -6.6278
Max Act: 6.3153. Min Act: -0.1700
Data Index: 735024 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6278. Min Range: -6.6278
Max Act: 6.3466. Min Act: -0.1700
Data Index: 3190930 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6278. Min Range: -6.6278
Max Act: 6.3466. Min Act: -0.1700
Data Index: 6665477 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6278. Min Range: -6.6278
Max Act: 6.2841. Min Act: -0.1700
Data Index: 5209424 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6278. Min Range: -6.6278
Max Act: 6.1903. Min Act: -0.1700
Data Index: 579410 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6278. Min Range: -6.6278
Max Act: 6.2216. Min Act: -0.1700
Data Index: 1045753 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6278. Min Range: -6.6278
Max Act: 6.2216. Min Act: -0.1700
Data Index: 4476795 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6278. Min Range: -6.6278
Max Act: 6.1278. Min Act: -0.1700
Data Index: 7444556 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6278. Min Range: -6.6278
Max Act: 6.1591. Min Act: -0.1700
Data Index: 5621752 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6278. Min Range: -6.6278
Max Act: 6.1278. Min Act: -0.1700
Data Index: 3587255 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6278. Min Range: -6.6278
Max Act: 6.0966. Min Act: -0.1700
Data Index: 3110946 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6278. Min Range: -6.6278
Max Act: 6.0966. Min Act: -0.1700
Data Index: 3016159 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6278. Min Range: -6.6278
Max Act: 6.0966. Min Act: -0.1700
Data Index: 7167584 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6278. Min Range: -6.6278
Max Act: 6.1278. Min Act: -0.1700
Data Index: 5804525 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6278. Min Range: -6.6278
Max Act: 6.0653. Min Act: -0.1700
Data Index: 6103463 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6278. Min Range: -6.6278
Max Act: 6.0341. Min Act: -0.1700
Data Index: 1727169 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6278. Min Range: -6.6278
Max Act: 6.0341. Min Act: -0.1700
Data Index: 6068640 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #19