Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3740 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1991. Min Range: -9.1991
Max Act: 9.1991. Min Act: -0.1700
Data Index: 5633052 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1991. Min Range: -9.1991
Max Act: 9.1991. Min Act: -0.1700
Data Index: 4093922 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1991. Min Range: -9.1991
Max Act: 9.1366. Min Act: -0.1700
Data Index: 6907899 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1991. Min Range: -9.1991
Max Act: 9.1366. Min Act: -0.1700
Data Index: 3841433 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1991. Min Range: -9.1991
Max Act: 9.0741. Min Act: -0.1700
Data Index: 1145362 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1991. Min Range: -9.1991
Max Act: 9.0116. Min Act: -0.1700
Data Index: 814269 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1991. Min Range: -9.1991
Max Act: 8.9491. Min Act: -0.1700
Data Index: 5647273 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1991. Min Range: -9.1991
Max Act: 8.8866. Min Act: -0.1700
Data Index: 5397585 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1991. Min Range: -9.1991
Max Act: 8.8866. Min Act: -0.1700
Data Index: 6432580 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1991. Min Range: -9.1991
Max Act: 8.8866. Min Act: -0.1700
Data Index: 6519528 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1991. Min Range: -9.1991
Max Act: 8.8866. Min Act: -0.1700
Data Index: 3084850 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1991. Min Range: -9.1991
Max Act: 8.8241. Min Act: -0.1700
Data Index: 2024100 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1991. Min Range: -9.1991
Max Act: 8.8241. Min Act: -0.1700
Data Index: 7575181 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1991. Min Range: -9.1991
Max Act: 8.8241. Min Act: -0.1700
Data Index: 5241215 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1991. Min Range: -9.1991
Max Act: 8.8241. Min Act: -0.1700
Data Index: 5922992 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1991. Min Range: -9.1991
Max Act: 8.8241. Min Act: -0.1700
Data Index: 4700054 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1991. Min Range: -9.1991
Max Act: 8.8241. Min Act: -0.1700
Data Index: 5538463 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1991. Min Range: -9.1991
Max Act: 8.7616. Min Act: -0.1700
Data Index: 3953798 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1991. Min Range: -9.1991
Max Act: 8.7616. Min Act: -0.1700
Data Index: 7011930 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1991. Min Range: -9.1991
Max Act: 8.7616. Min Act: -0.1700
Data Index: 3557163 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19