Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2973 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4439. Min Range: -9.4439
Max Act: 9.4439. Min Act: -0.1700
Data Index: 3607323 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4439. Min Range: -9.4439
Max Act: 9.3814. Min Act: -0.1700
Data Index: 6686113 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4439. Min Range: -9.4439
Max Act: 9.0064. Min Act: -0.1700
Data Index: 1968290 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4439. Min Range: -9.4439
Max Act: 8.8814. Min Act: -0.1700
Data Index: 4835243 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4439. Min Range: -9.4439
Max Act: 8.7564. Min Act: -0.1700
Data Index: 4486417 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4439. Min Range: -9.4439
Max Act: 8.7564. Min Act: -0.1700
Data Index: 4694705 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4439. Min Range: -9.4439
Max Act: 8.6939. Min Act: -0.1700
Data Index: 6717280 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4439. Min Range: -9.4439
Max Act: 8.6939. Min Act: -0.1700
Data Index: 4044660 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4439. Min Range: -9.4439
Max Act: 8.6314. Min Act: -0.1700
Data Index: 6693819 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4439. Min Range: -9.4439
Max Act: 8.6939. Min Act: -0.1700
Data Index: 5359786 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4439. Min Range: -9.4439
Max Act: 8.6314. Min Act: -0.1700
Data Index: 4701768 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4439. Min Range: -9.4439
Max Act: 8.6314. Min Act: -0.1700
Data Index: 6430410 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4439. Min Range: -9.4439
Max Act: 8.6314. Min Act: -0.1700
Data Index: 4773095 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4439. Min Range: -9.4439
Max Act: 8.6314. Min Act: -0.1700
Data Index: 2024998 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4439. Min Range: -9.4439
Max Act: 8.5689. Min Act: -0.1700
Data Index: 7125592 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4439. Min Range: -9.4439
Max Act: 8.5689. Min Act: -0.1700
Data Index: 8430680 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4439. Min Range: -9.4439
Max Act: 8.5064. Min Act: -0.1700
Data Index: 6137211 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4439. Min Range: -9.4439
Max Act: 8.4439. Min Act: -0.1700
Data Index: 6564642 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4439. Min Range: -9.4439
Max Act: 8.5689. Min Act: -0.1700
Data Index: 1769208 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4439. Min Range: -9.4439
Max Act: 8.5064. Min Act: -0.1700
Data Index: 424126 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #19