Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2286 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7358. Min Range: -7.7358
Max Act: 7.7358. Min Act: -0.1700
Data Index: 8444566 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7358. Min Range: -7.7358
Max Act: 7.6108. Min Act: -0.1700
Data Index: 6612013 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7358. Min Range: -7.7358
Max Act: 7.5796. Min Act: -0.1700
Data Index: 3994211 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7358. Min Range: -7.7358
Max Act: 7.5171. Min Act: -0.1700
Data Index: 6837127 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7358. Min Range: -7.7358
Max Act: 7.4858. Min Act: -0.1700
Data Index: 3431089 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7358. Min Range: -7.7358
Max Act: 7.4858. Min Act: -0.1700
Data Index: 1369911 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7358. Min Range: -7.7358
Max Act: 7.3608. Min Act: -0.1700
Data Index: 2534663 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7358. Min Range: -7.7358
Max Act: 7.3296. Min Act: -0.1700
Data Index: 1994817 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7358. Min Range: -7.7358
Max Act: 7.3296. Min Act: -0.1700
Data Index: 5821104 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7358. Min Range: -7.7358
Max Act: 7.2983. Min Act: -0.1700
Data Index: 1056916 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7358. Min Range: -7.7358
Max Act: 7.2671. Min Act: -0.1700
Data Index: 6315162 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7358. Min Range: -7.7358
Max Act: 7.2358. Min Act: -0.1700
Data Index: 4706977 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7358. Min Range: -7.7358
Max Act: 7.2046. Min Act: -0.1700
Data Index: 4372376 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7358. Min Range: -7.7358
Max Act: 7.2046. Min Act: -0.1700
Data Index: 5497845 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7358. Min Range: -7.7358
Max Act: 7.2046. Min Act: -0.1700
Data Index: 1208393 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7358. Min Range: -7.7358
Max Act: 7.1733. Min Act: -0.1700
Data Index: 36314 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7358. Min Range: -7.7358
Max Act: 7.1733. Min Act: -0.1700
Data Index: 491031 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7358. Min Range: -7.7358
Max Act: 7.1733. Min Act: -0.1700
Data Index: 3969648 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7358. Min Range: -7.7358
Max Act: 7.1421. Min Act: -0.1700
Data Index: 6604264 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7358. Min Range: -7.7358
Max Act: 7.1421. Min Act: -0.1700
Data Index: 5149943 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19