Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3643 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3474. Min Range: -10.3474
Max Act: 10.3474. Min Act: -0.1700
Data Index: 5358596 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3474. Min Range: -10.3474
Max Act: 10.2849. Min Act: -0.1700
Data Index: 5134725 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3474. Min Range: -10.3474
Max Act: 10.2224. Min Act: -0.1700
Data Index: 2914339 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3474. Min Range: -10.3474
Max Act: 10.0974. Min Act: -0.1700
Data Index: 524606 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3474. Min Range: -10.3474
Max Act: 10.1599. Min Act: -0.1700
Data Index: 4258657 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3474. Min Range: -10.3474
Max Act: 10.0349. Min Act: -0.1700
Data Index: 6903039 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3474. Min Range: -10.3474
Max Act: 10.0349. Min Act: -0.1700
Data Index: 5237780 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3474. Min Range: -10.3474
Max Act: 9.9724. Min Act: -0.1700
Data Index: 6286700 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3474. Min Range: -10.3474
Max Act: 9.9099. Min Act: -0.1700
Data Index: 3435982 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3474. Min Range: -10.3474
Max Act: 9.9724. Min Act: -0.1700
Data Index: 1244577 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3474. Min Range: -10.3474
Max Act: 9.9099. Min Act: -0.1700
Data Index: 6079754 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3474. Min Range: -10.3474
Max Act: 9.9099. Min Act: -0.1700
Data Index: 1136086 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3474. Min Range: -10.3474
Max Act: 9.9099. Min Act: -0.1700
Data Index: 1334255 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3474. Min Range: -10.3474
Max Act: 9.9099. Min Act: -0.1700
Data Index: 3084285 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3474. Min Range: -10.3474
Max Act: 9.9099. Min Act: -0.1700
Data Index: 2919028 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3474. Min Range: -10.3474
Max Act: 9.9099. Min Act: -0.1700
Data Index: 7690656 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3474. Min Range: -10.3474
Max Act: 9.8474. Min Act: -0.1700
Data Index: 5156601 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3474. Min Range: -10.3474
Max Act: 9.7849. Min Act: -0.1700
Data Index: 615207 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3474. Min Range: -10.3474
Max Act: 9.7224. Min Act: -0.1700
Data Index: 1551235 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3474. Min Range: -10.3474
Max Act: 9.7224. Min Act: -0.1700
Data Index: 629848 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19