Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 48 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3190. Min Range: -5.3190
Max Act: 5.3190. Min Act: -0.1700
Data Index: 2045567 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3190. Min Range: -5.3190
Max Act: 5.3190. Min Act: -0.1700
Data Index: 867211 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3190. Min Range: -5.3190
Max Act: 5.2252. Min Act: -0.1700
Data Index: 8825131 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3190. Min Range: -5.3190
Max Act: 5.2252. Min Act: -0.1700
Data Index: 4714843 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3190. Min Range: -5.3190
Max Act: 5.1940. Min Act: -0.1700
Data Index: 6907785 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3190. Min Range: -5.3190
Max Act: 5.1940. Min Act: -0.1700
Data Index: 4893363 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3190. Min Range: -5.3190
Max Act: 5.1627. Min Act: -0.1700
Data Index: 6907786 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3190. Min Range: -5.3190
Max Act: 5.1627. Min Act: -0.1700
Data Index: 4748400 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3190. Min Range: -5.3190
Max Act: 5.1627. Min Act: -0.1700
Data Index: 6602157 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3190. Min Range: -5.3190
Max Act: 5.1627. Min Act: -0.1700
Data Index: 3483027 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3190. Min Range: -5.3190
Max Act: 5.1315. Min Act: -0.1700
Data Index: 4500910 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3190. Min Range: -5.3190
Max Act: 5.1315. Min Act: -0.1700
Data Index: 3067525 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3190. Min Range: -5.3190
Max Act: 5.1315. Min Act: -0.1700
Data Index: 8098508 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3190. Min Range: -5.3190
Max Act: 5.1002. Min Act: -0.1700
Data Index: 7754270 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3190. Min Range: -5.3190
Max Act: 5.1002. Min Act: -0.1700
Data Index: 3010895 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3190. Min Range: -5.3190
Max Act: 5.0690. Min Act: -0.1700
Data Index: 921190 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3190. Min Range: -5.3190
Max Act: 5.0377. Min Act: -0.1700
Data Index: 1405728 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3190. Min Range: -5.3190
Max Act: 5.0377. Min Act: -0.1700
Data Index: 7789733 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3190. Min Range: -5.3190
Max Act: 5.0377. Min Act: -0.1700
Data Index: 4001113 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3190. Min Range: -5.3190
Max Act: 5.0377. Min Act: -0.1700
Data Index: 2480123 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19