Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5531 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6238. Min Range: -5.6238
Max Act: 5.6238. Min Act: -0.1700
Data Index: 7104726 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6238. Min Range: -5.6238
Max Act: 5.2176. Min Act: -0.1700
Data Index: 2226681 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6238. Min Range: -5.6238
Max Act: 5.1238. Min Act: -0.1700
Data Index: 1258736 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6238. Min Range: -5.6238
Max Act: 5.1238. Min Act: -0.1700
Data Index: 3711320 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6238. Min Range: -5.6238
Max Act: 4.9988. Min Act: -0.1700
Data Index: 2657128 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6238. Min Range: -5.6238
Max Act: 4.9676. Min Act: -0.1700
Data Index: 2226680 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6238. Min Range: -5.6238
Max Act: 4.9363. Min Act: -0.1700
Data Index: 8042160 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6238. Min Range: -5.6238
Max Act: 4.9676. Min Act: -0.1700
Data Index: 1606011 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6238. Min Range: -5.6238
Max Act: 4.8426. Min Act: -0.1700
Data Index: 2658640 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6238. Min Range: -5.6238
Max Act: 4.8426. Min Act: -0.1700
Data Index: 8589738 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6238. Min Range: -5.6238
Max Act: 4.8113. Min Act: -0.1700
Data Index: 3946265 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6238. Min Range: -5.6238
Max Act: 4.7801. Min Act: -0.1700
Data Index: 3668666 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6238. Min Range: -5.6238
Max Act: 4.7488. Min Act: -0.1700
Data Index: 7564549 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6238. Min Range: -5.6238
Max Act: 4.7801. Min Act: -0.1700
Data Index: 4635674 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6238. Min Range: -5.6238
Max Act: 4.7801. Min Act: -0.1700
Data Index: 5616423 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6238. Min Range: -5.6238
Max Act: 4.7488. Min Act: -0.1700
Data Index: 1466001 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6238. Min Range: -5.6238
Max Act: 4.7488. Min Act: -0.1700
Data Index: 1258737 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6238. Min Range: -5.6238
Max Act: 4.7488. Min Act: -0.1700
Data Index: 8442436 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6238. Min Range: -5.6238
Max Act: 4.7176. Min Act: -0.1700
Data Index: 4376971 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6238. Min Range: -5.6238
Max Act: 4.7176. Min Act: -0.1700
Data Index: 2511024 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19