Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5645 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9040. Min Range: -6.9040
Max Act: 6.9040. Min Act: -0.1700
Data Index: 2530710 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9040. Min Range: -6.9040
Max Act: 6.8415. Min Act: -0.1700
Data Index: 297805 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9040. Min Range: -6.9040
Max Act: 6.8103. Min Act: -0.1700
Data Index: 2687074 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9040. Min Range: -6.9040
Max Act: 6.7478. Min Act: -0.1700
Data Index: 8453898 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9040. Min Range: -6.9040
Max Act: 6.7165. Min Act: -0.1700
Data Index: 8125114 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9040. Min Range: -6.9040
Max Act: 6.6540. Min Act: -0.1700
Data Index: 4620127 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9040. Min Range: -6.9040
Max Act: 6.6540. Min Act: -0.1700
Data Index: 1345521 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9040. Min Range: -6.9040
Max Act: 6.5603. Min Act: -0.1700
Data Index: 7413464 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9040. Min Range: -6.9040
Max Act: 6.5603. Min Act: -0.1700
Data Index: 5178413 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9040. Min Range: -6.9040
Max Act: 6.5603. Min Act: -0.1700
Data Index: 3750046 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9040. Min Range: -6.9040
Max Act: 6.5290. Min Act: -0.1700
Data Index: 4635456 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9040. Min Range: -6.9040
Max Act: 6.5603. Min Act: -0.1700
Data Index: 32673 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9040. Min Range: -6.9040
Max Act: 6.5603. Min Act: -0.1700
Data Index: 3615920 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9040. Min Range: -6.9040
Max Act: 6.5290. Min Act: -0.1700
Data Index: 7025667 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9040. Min Range: -6.9040
Max Act: 6.4978. Min Act: -0.1700
Data Index: 1687327 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9040. Min Range: -6.9040
Max Act: 6.4978. Min Act: -0.1700
Data Index: 1673702 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9040. Min Range: -6.9040
Max Act: 6.4665. Min Act: -0.1700
Data Index: 4149887 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9040. Min Range: -6.9040
Max Act: 6.4665. Min Act: -0.1700
Data Index: 7527842 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9040. Min Range: -6.9040
Max Act: 6.4665. Min Act: -0.1700
Data Index: 6450561 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9040. Min Range: -6.9040
Max Act: 6.4665. Min Act: -0.1700
Data Index: 719310 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #19