Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2191 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6395. Min Range: -4.6395
Max Act: 4.6395. Min Act: -0.1700
Data Index: 1861965 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6395. Min Range: -4.6395
Max Act: 4.5770. Min Act: -0.1700
Data Index: 7823189 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6395. Min Range: -4.6395
Max Act: 4.5770. Min Act: -0.1700
Data Index: 1707101 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6395. Min Range: -4.6395
Max Act: 4.5770. Min Act: -0.1700
Data Index: 1566267 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6395. Min Range: -4.6395
Max Act: 4.5458. Min Act: -0.1700
Data Index: 6212196 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6395. Min Range: -4.6395
Max Act: 4.5458. Min Act: -0.1700
Data Index: 351323 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6395. Min Range: -4.6395
Max Act: 4.5458. Min Act: -0.1700
Data Index: 5527522 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6395. Min Range: -4.6395
Max Act: 4.5458. Min Act: -0.1700
Data Index: 4135792 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6395. Min Range: -4.6395
Max Act: 4.5145. Min Act: -0.1700
Data Index: 3139770 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6395. Min Range: -4.6395
Max Act: 4.5145. Min Act: -0.1700
Data Index: 2149970 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6395. Min Range: -4.6395
Max Act: 4.5145. Min Act: -0.1700
Data Index: 554360 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6395. Min Range: -4.6395
Max Act: 4.4833. Min Act: -0.1700
Data Index: 4167253 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6395. Min Range: -4.6395
Max Act: 4.4833. Min Act: -0.1700
Data Index: 5019981 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6395. Min Range: -4.6395
Max Act: 4.4833. Min Act: -0.1700
Data Index: 5355115 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6395. Min Range: -4.6395
Max Act: 4.4833. Min Act: -0.1700
Data Index: 8426667 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6395. Min Range: -4.6395
Max Act: 4.4833. Min Act: -0.1700
Data Index: 5618977 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6395. Min Range: -4.6395
Max Act: 4.4520. Min Act: -0.1700
Data Index: 4096345 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6395. Min Range: -4.6395
Max Act: 4.4520. Min Act: -0.1700
Data Index: 5368132 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6395. Min Range: -4.6395
Max Act: 4.4520. Min Act: -0.1700
Data Index: 3648365 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6395. Min Range: -4.6395
Max Act: 4.4520. Min Act: -0.1700
Data Index: 2327005 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19