Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1460 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9990. Min Range: -5.9990
Max Act: 5.9990. Min Act: -0.1700
Data Index: 4680413 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9990. Min Range: -5.9990
Max Act: 5.9053. Min Act: -0.1700
Data Index: 6258278 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9990. Min Range: -5.9990
Max Act: 5.8740. Min Act: -0.1700
Data Index: 517267 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9990. Min Range: -5.9990
Max Act: 5.8740. Min Act: -0.1700
Data Index: 8227835 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9990. Min Range: -5.9990
Max Act: 5.8115. Min Act: -0.1700
Data Index: 4900994 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9990. Min Range: -5.9990
Max Act: 5.8428. Min Act: -0.1700
Data Index: 8176490 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9990. Min Range: -5.9990
Max Act: 5.7803. Min Act: -0.1700
Data Index: 4915201 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9990. Min Range: -5.9990
Max Act: 5.7490. Min Act: -0.1700
Data Index: 1231409 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9990. Min Range: -5.9990
Max Act: 5.6865. Min Act: -0.1700
Data Index: 6513991 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9990. Min Range: -5.9990
Max Act: 5.6865. Min Act: -0.1700
Data Index: 10047 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9990. Min Range: -5.9990
Max Act: 5.6865. Min Act: -0.1700
Data Index: 4616727 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9990. Min Range: -5.9990
Max Act: 5.6865. Min Act: -0.1700
Data Index: 3919062 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9990. Min Range: -5.9990
Max Act: 5.6553. Min Act: -0.1700
Data Index: 2892886 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9990. Min Range: -5.9990
Max Act: 5.6553. Min Act: -0.1700
Data Index: 2623589 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9990. Min Range: -5.9990
Max Act: 5.6553. Min Act: -0.1700
Data Index: 7520184 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9990. Min Range: -5.9990
Max Act: 5.5928. Min Act: -0.1700
Data Index: 4243575 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9990. Min Range: -5.9990
Max Act: 5.6240. Min Act: -0.1700
Data Index: 4729445 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9990. Min Range: -5.9990
Max Act: 5.5928. Min Act: -0.1700
Data Index: 395880 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9990. Min Range: -5.9990
Max Act: 5.5303. Min Act: -0.1700
Data Index: 7378339 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9990. Min Range: -5.9990
Max Act: 5.5303. Min Act: -0.1700
Data Index: 157381 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19