Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1804 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7325. Min Range: -4.7325
Max Act: 4.7325. Min Act: -0.1700
Data Index: 7340977 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7325. Min Range: -4.7325
Max Act: 4.3887. Min Act: -0.1700
Data Index: 1228238 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7325. Min Range: -4.7325
Max Act: 4.3575. Min Act: -0.1700
Data Index: 6153444 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7325. Min Range: -4.7325
Max Act: 4.3262. Min Act: -0.1700
Data Index: 1642835 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7325. Min Range: -4.7325
Max Act: 4.2637. Min Act: -0.1700
Data Index: 6677304 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7325. Min Range: -4.7325
Max Act: 4.2325. Min Act: -0.1700
Data Index: 5197680 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7325. Min Range: -4.7325
Max Act: 4.2637. Min Act: -0.1700
Data Index: 2735260 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7325. Min Range: -4.7325
Max Act: 4.2325. Min Act: -0.1700
Data Index: 7364891 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7325. Min Range: -4.7325
Max Act: 4.2325. Min Act: -0.1700
Data Index: 1893601 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7325. Min Range: -4.7325
Max Act: 4.2012. Min Act: -0.1700
Data Index: 1089297 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7325. Min Range: -4.7325
Max Act: 4.2012. Min Act: -0.1700
Data Index: 3244621 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7325. Min Range: -4.7325
Max Act: 4.2012. Min Act: -0.1700
Data Index: 1618678 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7325. Min Range: -4.7325
Max Act: 4.1700. Min Act: -0.1700
Data Index: 2078940 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7325. Min Range: -4.7325
Max Act: 4.1700. Min Act: -0.1700
Data Index: 5205272 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7325. Min Range: -4.7325
Max Act: 4.2012. Min Act: -0.1700
Data Index: 4058930 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7325. Min Range: -4.7325
Max Act: 4.1387. Min Act: -0.1700
Data Index: 3923925 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7325. Min Range: -4.7325
Max Act: 4.1387. Min Act: -0.1700
Data Index: 1650101 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7325. Min Range: -4.7325
Max Act: 4.1387. Min Act: -0.1700
Data Index: 8306674 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7325. Min Range: -4.7325
Max Act: 4.1387. Min Act: -0.1700
Data Index: 129899 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7325. Min Range: -4.7325
Max Act: 4.1387. Min Act: -0.1700
Data Index: 8615539 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19