Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2801 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6421. Min Range: -5.6421
Max Act: 5.6421. Min Act: -0.1700
Data Index: 6748274 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6421. Min Range: -5.6421
Max Act: 5.5483. Min Act: -0.1700
Data Index: 2856515 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6421. Min Range: -5.6421
Max Act: 5.5171. Min Act: -0.1700
Data Index: 3325599 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6421. Min Range: -5.6421
Max Act: 5.5171. Min Act: -0.1700
Data Index: 6733622 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6421. Min Range: -5.6421
Max Act: 5.3296. Min Act: -0.1700
Data Index: 1068792 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6421. Min Range: -5.6421
Max Act: 5.3296. Min Act: -0.1700
Data Index: 2468079 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6421. Min Range: -5.6421
Max Act: 5.2983. Min Act: -0.1700
Data Index: 4777547 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6421. Min Range: -5.6421
Max Act: 5.2983. Min Act: -0.1700
Data Index: 3510043 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6421. Min Range: -5.6421
Max Act: 5.2358. Min Act: -0.1700
Data Index: 713613 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6421. Min Range: -5.6421
Max Act: 5.1733. Min Act: -0.1700
Data Index: 4346005 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6421. Min Range: -5.6421
Max Act: 5.1733. Min Act: -0.1700
Data Index: 3886751 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6421. Min Range: -5.6421
Max Act: 5.1733. Min Act: -0.1700
Data Index: 681169 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6421. Min Range: -5.6421
Max Act: 5.1733. Min Act: -0.1700
Data Index: 6559843 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6421. Min Range: -5.6421
Max Act: 5.1733. Min Act: -0.1700
Data Index: 8430397 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6421. Min Range: -5.6421
Max Act: 5.0796. Min Act: -0.1700
Data Index: 1028084 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6421. Min Range: -5.6421
Max Act: 5.1108. Min Act: -0.1700
Data Index: 3401595 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6421. Min Range: -5.6421
Max Act: 5.1108. Min Act: -0.1700
Data Index: 7218085 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6421. Min Range: -5.6421
Max Act: 5.1108. Min Act: -0.1700
Data Index: 692488 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6421. Min Range: -5.6421
Max Act: 5.0796. Min Act: -0.1700
Data Index: 647524 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6421. Min Range: -5.6421
Max Act: 5.0796. Min Act: -0.1700
Data Index: 1120066 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19