Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3357 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6502. Min Range: -8.6502
Max Act: 8.6502. Min Act: -0.1700
Data Index: 6163788 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6502. Min Range: -8.6502
Max Act: 8.5877. Min Act: -0.1700
Data Index: 6163800 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6502. Min Range: -8.6502
Max Act: 7.8064. Min Act: -0.1700
Data Index: 8548409 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6502. Min Range: -8.6502
Max Act: 7.8377. Min Act: -0.1700
Data Index: 8580149 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6502. Min Range: -8.6502
Max Act: 7.7439. Min Act: -0.1700
Data Index: 832751 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6502. Min Range: -8.6502
Max Act: 7.7127. Min Act: -0.1700
Data Index: 1521337 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6502. Min Range: -8.6502
Max Act: 7.7127. Min Act: -0.1700
Data Index: 141021 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6502. Min Range: -8.6502
Max Act: 7.6814. Min Act: -0.1700
Data Index: 5271991 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6502. Min Range: -8.6502
Max Act: 7.6189. Min Act: -0.1700
Data Index: 2737874 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6502. Min Range: -8.6502
Max Act: 7.6189. Min Act: -0.1700
Data Index: 5970740 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6502. Min Range: -8.6502
Max Act: 7.5564. Min Act: -0.1700
Data Index: 8590050 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6502. Min Range: -8.6502
Max Act: 7.5877. Min Act: -0.1700
Data Index: 6379575 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6502. Min Range: -8.6502
Max Act: 7.5877. Min Act: -0.1700
Data Index: 6296260 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6502. Min Range: -8.6502
Max Act: 7.5564. Min Act: -0.1700
Data Index: 5449647 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6502. Min Range: -8.6502
Max Act: 7.5877. Min Act: -0.1700
Data Index: 4895712 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6502. Min Range: -8.6502
Max Act: 7.5564. Min Act: -0.1700
Data Index: 6722890 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6502. Min Range: -8.6502
Max Act: 7.5564. Min Act: -0.1700
Data Index: 3706756 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6502. Min Range: -8.6502
Max Act: 7.5252. Min Act: -0.1700
Data Index: 1613715 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6502. Min Range: -8.6502
Max Act: 7.5252. Min Act: -0.1700
Data Index: 6202817 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6502. Min Range: -8.6502
Max Act: 7.5252. Min Act: -0.1700
Data Index: 2925844 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19