Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3708 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8476. Min Range: -3.8476
Max Act: 3.8163. Min Act: -0.1700
Data Index: 4858759 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8476. Min Range: -3.8476
Max Act: 3.8476. Min Act: -0.1700
Data Index: 5642212 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8476. Min Range: -3.8476
Max Act: 3.8163. Min Act: -0.1700
Data Index: 4772826 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8476. Min Range: -3.8476
Max Act: 3.7538. Min Act: -0.1700
Data Index: 6338595 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8476. Min Range: -3.8476
Max Act: 3.7225. Min Act: -0.1700
Data Index: 2688939 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8476. Min Range: -3.8476
Max Act: 3.7225. Min Act: -0.1700
Data Index: 6688052 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8476. Min Range: -3.8476
Max Act: 3.6912. Min Act: -0.1700
Data Index: 306000 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8476. Min Range: -3.8476
Max Act: 3.6912. Min Act: -0.1700
Data Index: 1667906 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8476. Min Range: -3.8476
Max Act: 3.6756. Min Act: -0.1700
Data Index: 7014163 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8476. Min Range: -3.8476
Max Act: 3.6599. Min Act: -0.1700
Data Index: 4663960 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8476. Min Range: -3.8476
Max Act: 3.6599. Min Act: -0.1700
Data Index: 170654 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8476. Min Range: -3.8476
Max Act: 3.6443. Min Act: -0.1700
Data Index: 4441995 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8476. Min Range: -3.8476
Max Act: 3.6286. Min Act: -0.1700
Data Index: 8352808 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8476. Min Range: -3.8476
Max Act: 3.6443. Min Act: -0.1700
Data Index: 4062650 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8476. Min Range: -3.8476
Max Act: 3.6286. Min Act: -0.1700
Data Index: 7468865 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8476. Min Range: -3.8476
Max Act: 3.6130. Min Act: -0.1700
Data Index: 4476220 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8476. Min Range: -3.8476
Max Act: 3.5973. Min Act: -0.1700
Data Index: 766200 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8476. Min Range: -3.8476
Max Act: 3.5973. Min Act: -0.1700
Data Index: 894434 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8476. Min Range: -3.8476
Max Act: 3.5817. Min Act: -0.1700
Data Index: 8380646 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8476. Min Range: -3.8476
Max Act: 3.5660. Min Act: -0.1700
Data Index: 400011 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #19