Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5610 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.7351. Min Act: -0.1700
Data Index: 4013652 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.6726. Min Act: -0.1700
Data Index: 23790 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.6101. Min Act: -0.1700
Data Index: 6756294 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.6414. Min Act: -0.1700
Data Index: 8458963 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.6414. Min Act: -0.1700
Data Index: 7227766 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.6101. Min Act: -0.1700
Data Index: 788945 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.5476. Min Act: -0.1700
Data Index: 3825972 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.5476. Min Act: -0.1700
Data Index: 686833 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.5164. Min Act: -0.1700
Data Index: 4777988 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.5476. Min Act: -0.1700
Data Index: 7765573 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.5476. Min Act: -0.1700
Data Index: 4228897 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.5476. Min Act: -0.1700
Data Index: 2793277 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.5164. Min Act: -0.1700
Data Index: 7262828 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.5476. Min Act: -0.1700
Data Index: 7930659 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.5164. Min Act: -0.1700
Data Index: 7615629 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.5164. Min Act: -0.1700
Data Index: 6923395 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.5164. Min Act: -0.1700
Data Index: 7919099 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.5164. Min Act: -0.1700
Data Index: 2024393 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.5164. Min Act: -0.1700
Data Index: 3683378 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.4851. Min Act: -0.1700
Data Index: 3862163 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19