Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2908 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9548. Min Range: -6.9548
Max Act: 6.9548. Min Act: -0.1700
Data Index: 1049803 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9548. Min Range: -6.9548
Max Act: 6.9236. Min Act: -0.1700
Data Index: 8742189 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9548. Min Range: -6.9548
Max Act: 6.8611. Min Act: -0.1700
Data Index: 5328938 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9548. Min Range: -6.9548
Max Act: 6.6736. Min Act: -0.1700
Data Index: 6419473 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9548. Min Range: -6.9548
Max Act: 6.6736. Min Act: -0.1700
Data Index: 1438304 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9548. Min Range: -6.9548
Max Act: 6.5798. Min Act: -0.1700
Data Index: 2678396 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9548. Min Range: -6.9548
Max Act: 6.5486. Min Act: -0.1700
Data Index: 8630136 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9548. Min Range: -6.9548
Max Act: 6.4861. Min Act: -0.1700
Data Index: 4677091 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9548. Min Range: -6.9548
Max Act: 6.4861. Min Act: -0.1700
Data Index: 6849236 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9548. Min Range: -6.9548
Max Act: 6.4236. Min Act: -0.1700
Data Index: 8679666 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9548. Min Range: -6.9548
Max Act: 6.3923. Min Act: -0.1700
Data Index: 6295182 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9548. Min Range: -6.9548
Max Act: 6.3611. Min Act: -0.1700
Data Index: 318732 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9548. Min Range: -6.9548
Max Act: 6.3298. Min Act: -0.1700
Data Index: 5170405 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9548. Min Range: -6.9548
Max Act: 6.3611. Min Act: -0.1700
Data Index: 333608 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9548. Min Range: -6.9548
Max Act: 6.2986. Min Act: -0.1700
Data Index: 8127593 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9548. Min Range: -6.9548
Max Act: 6.2986. Min Act: -0.1700
Data Index: 7543908 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9548. Min Range: -6.9548
Max Act: 6.2673. Min Act: -0.1700
Data Index: 5030578 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9548. Min Range: -6.9548
Max Act: 6.2673. Min Act: -0.1700
Data Index: 6316245 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9548. Min Range: -6.9548
Max Act: 6.2048. Min Act: -0.1700
Data Index: 6219153 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9548. Min Range: -6.9548
Max Act: 6.2361. Min Act: -0.1700
Data Index: 8696579 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #19