Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6379 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8283. Min Range: -7.8283
Max Act: 7.8283. Min Act: -0.1700
Data Index: 5380250 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8283. Min Range: -7.8283
Max Act: 7.7658. Min Act: -0.1700
Data Index: 7939532 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8283. Min Range: -7.8283
Max Act: 7.7658. Min Act: -0.1700
Data Index: 6553542 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8283. Min Range: -7.8283
Max Act: 7.6408. Min Act: -0.1700
Data Index: 2038444 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8283. Min Range: -7.8283
Max Act: 7.6720. Min Act: -0.1700
Data Index: 6424923 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8283. Min Range: -7.8283
Max Act: 7.6095. Min Act: -0.1700
Data Index: 6785603 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8283. Min Range: -7.8283
Max Act: 7.5470. Min Act: -0.1700
Data Index: 75342 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8283. Min Range: -7.8283
Max Act: 7.5470. Min Act: -0.1700
Data Index: 6908046 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8283. Min Range: -7.8283
Max Act: 7.5158. Min Act: -0.1700
Data Index: 1637461 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8283. Min Range: -7.8283
Max Act: 7.5158. Min Act: -0.1700
Data Index: 1307472 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8283. Min Range: -7.8283
Max Act: 7.4220. Min Act: -0.1700
Data Index: 5953243 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8283. Min Range: -7.8283
Max Act: 7.4220. Min Act: -0.1700
Data Index: 118415 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8283. Min Range: -7.8283
Max Act: 7.3908. Min Act: -0.1700
Data Index: 1190356 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8283. Min Range: -7.8283
Max Act: 7.3908. Min Act: -0.1700
Data Index: 3214837 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8283. Min Range: -7.8283
Max Act: 7.3908. Min Act: -0.1700
Data Index: 1846277 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8283. Min Range: -7.8283
Max Act: 7.4220. Min Act: -0.1700
Data Index: 46196 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8283. Min Range: -7.8283
Max Act: 7.3908. Min Act: -0.1700
Data Index: 1336910 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8283. Min Range: -7.8283
Max Act: 7.3595. Min Act: -0.1700
Data Index: 5344223 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8283. Min Range: -7.8283
Max Act: 7.3595. Min Act: -0.1700
Data Index: 6941427 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8283. Min Range: -7.8283
Max Act: 7.3283. Min Act: -0.1700
Data Index: 1861850 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #19