Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 554 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6811. Min Range: -3.6811
Max Act: 3.6811. Min Act: -0.1700
Data Index: 4616410 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6811. Min Range: -3.6811
Max Act: 3.6342. Min Act: -0.1700
Data Index: 6806389 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6811. Min Range: -3.6811
Max Act: 3.5246. Min Act: -0.1700
Data Index: 5235677 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6811. Min Range: -3.6811
Max Act: 3.5246. Min Act: -0.1700
Data Index: 3391901 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6811. Min Range: -3.6811
Max Act: 3.5246. Min Act: -0.1700
Data Index: 8424475 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6811. Min Range: -3.6811
Max Act: 3.5090. Min Act: -0.1700
Data Index: 5203403 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6811. Min Range: -3.6811
Max Act: 3.4933. Min Act: -0.1700
Data Index: 2653618 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6811. Min Range: -3.6811
Max Act: 3.4776. Min Act: -0.1700
Data Index: 6635796 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6811. Min Range: -3.6811
Max Act: 3.4776. Min Act: -0.1700
Data Index: 7353720 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6811. Min Range: -3.6811
Max Act: 3.4776. Min Act: -0.1700
Data Index: 7658803 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6811. Min Range: -3.6811
Max Act: 3.4620. Min Act: -0.1700
Data Index: 2496249 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6811. Min Range: -3.6811
Max Act: 3.4463. Min Act: -0.1700
Data Index: 3964000 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6811. Min Range: -3.6811
Max Act: 3.4306. Min Act: -0.1700
Data Index: 1341973 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6811. Min Range: -3.6811
Max Act: 3.4306. Min Act: -0.1700
Data Index: 4948584 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6811. Min Range: -3.6811
Max Act: 3.4463. Min Act: -0.1700
Data Index: 4084423 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6811. Min Range: -3.6811
Max Act: 3.4306. Min Act: -0.1700
Data Index: 2649722 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6811. Min Range: -3.6811
Max Act: 3.4463. Min Act: -0.1700
Data Index: 6471368 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6811. Min Range: -3.6811
Max Act: 3.4306. Min Act: -0.1700
Data Index: 8020125 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6811. Min Range: -3.6811
Max Act: 3.4149. Min Act: -0.1700
Data Index: 2013266 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6811. Min Range: -3.6811
Max Act: 3.4149. Min Act: -0.1700
Data Index: 6086815 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19