Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3527 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7020. Min Range: -7.7020
Max Act: 7.7020. Min Act: -0.1700
Data Index: 8010450 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7020. Min Range: -7.7020
Max Act: 7.6707. Min Act: -0.1700
Data Index: 454569 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7020. Min Range: -7.7020
Max Act: 7.5457. Min Act: -0.1700
Data Index: 7293528 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7020. Min Range: -7.7020
Max Act: 7.4832. Min Act: -0.1700
Data Index: 2373952 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7020. Min Range: -7.7020
Max Act: 7.4520. Min Act: -0.1700
Data Index: 6088128 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7020. Min Range: -7.7020
Max Act: 7.4207. Min Act: -0.1700
Data Index: 1792693 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7020. Min Range: -7.7020
Max Act: 7.4207. Min Act: -0.1700
Data Index: 3359831 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7020. Min Range: -7.7020
Max Act: 7.4520. Min Act: -0.1700
Data Index: 4646159 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7020. Min Range: -7.7020
Max Act: 7.3582. Min Act: -0.1700
Data Index: 5275330 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7020. Min Range: -7.7020
Max Act: 7.3270. Min Act: -0.1700
Data Index: 6914484 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7020. Min Range: -7.7020
Max Act: 7.3270. Min Act: -0.1700
Data Index: 8145140 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7020. Min Range: -7.7020
Max Act: 7.3270. Min Act: -0.1700
Data Index: 417088 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7020. Min Range: -7.7020
Max Act: 7.2645. Min Act: -0.1700
Data Index: 7390978 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7020. Min Range: -7.7020
Max Act: 7.2957. Min Act: -0.1700
Data Index: 5029944 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7020. Min Range: -7.7020
Max Act: 7.2645. Min Act: -0.1700
Data Index: 5000904 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7020. Min Range: -7.7020
Max Act: 7.2332. Min Act: -0.1700
Data Index: 8594892 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7020. Min Range: -7.7020
Max Act: 7.2332. Min Act: -0.1700
Data Index: 7467253 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7020. Min Range: -7.7020
Max Act: 7.2020. Min Act: -0.1700
Data Index: 8832232 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7020. Min Range: -7.7020
Max Act: 7.1707. Min Act: -0.1700
Data Index: 1090295 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7020. Min Range: -7.7020
Max Act: 7.2020. Min Act: -0.1700
Data Index: 700510 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19