Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3568 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.8319. Min Act: -0.1700
Data Index: 7110306 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.8006. Min Act: -0.1700
Data Index: 3286848 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.7069. Min Act: -0.1700
Data Index: 7014312 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.7069. Min Act: -0.1700
Data Index: 2847552 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.7069. Min Act: -0.1700
Data Index: 8613025 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.7069. Min Act: -0.1700
Data Index: 6128707 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.7069. Min Act: -0.1700
Data Index: 8178546 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.6444. Min Act: -0.1700
Data Index: 2938077 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.6444. Min Act: -0.1700
Data Index: 8621794 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.6756. Min Act: -0.1700
Data Index: 6446289 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.7069. Min Act: -0.1700
Data Index: 5448326 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.6756. Min Act: -0.1700
Data Index: 540427 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.6756. Min Act: -0.1700
Data Index: 837699 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.6756. Min Act: -0.1700
Data Index: 2639155 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.6756. Min Act: -0.1700
Data Index: 2624419 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.7069. Min Act: -0.1700
Data Index: 5436968 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.6756. Min Act: -0.1700
Data Index: 4774624 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.6444. Min Act: -0.1699
Data Index: 7970526 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.6756. Min Act: -0.1700
Data Index: 1000628 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.6444. Min Act: -0.1700
Data Index: 1644775 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19