Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3546 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1349. Min Range: -4.1349
Max Act: 4.1349. Min Act: -0.1700
Data Index: 28612 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1349. Min Range: -4.1349
Max Act: 4.0724. Min Act: -0.1700
Data Index: 3375849 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1349. Min Range: -4.1349
Max Act: 3.9786. Min Act: -0.1700
Data Index: 2376926 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1349. Min Range: -4.1349
Max Act: 3.9474. Min Act: -0.1700
Data Index: 4239568 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1349. Min Range: -4.1349
Max Act: 3.8536. Min Act: -0.1700
Data Index: 1060330 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1349. Min Range: -4.1349
Max Act: 3.8223. Min Act: -0.1700
Data Index: 8638804 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1349. Min Range: -4.1349
Max Act: 3.8223. Min Act: -0.1700
Data Index: 6385921 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1349. Min Range: -4.1349
Max Act: 3.7597. Min Act: -0.1700
Data Index: 2475253 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1349. Min Range: -4.1349
Max Act: 3.7597. Min Act: -0.1700
Data Index: 4277958 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1349. Min Range: -4.1349
Max Act: 3.7285. Min Act: -0.1700
Data Index: 8289002 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1349. Min Range: -4.1349
Max Act: 3.7285. Min Act: -0.1700
Data Index: 8640556 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1349. Min Range: -4.1349
Max Act: 3.6972. Min Act: -0.1700
Data Index: 31222 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1349. Min Range: -4.1349
Max Act: 3.6659. Min Act: -0.1700
Data Index: 7867039 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1349. Min Range: -4.1349
Max Act: 3.6659. Min Act: -0.1700
Data Index: 6798891 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1349. Min Range: -4.1349
Max Act: 3.6502. Min Act: -0.1700
Data Index: 3793955 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1349. Min Range: -4.1349
Max Act: 3.6502. Min Act: -0.1700
Data Index: 657011 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1349. Min Range: -4.1349
Max Act: 3.6502. Min Act: -0.1700
Data Index: 6500528 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1349. Min Range: -4.1349
Max Act: 3.6502. Min Act: -0.1700
Data Index: 5980468 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1349. Min Range: -4.1349
Max Act: 3.6346. Min Act: -0.1700
Data Index: 3345611 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1349. Min Range: -4.1349
Max Act: 3.6346. Min Act: -0.1700
Data Index: 7066663 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19