Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2705 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.6892. Min Range: -11.6892
Max Act: 11.6892. Min Act: -0.1700
Data Index: 3172911 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.6892. Min Range: -11.6892
Max Act: 11.4392. Min Act: -0.1700
Data Index: 8471305 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.6892. Min Range: -11.6892
Max Act: 11.1892. Min Act: -0.1700
Data Index: 4887805 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.6892. Min Range: -11.6892
Max Act: 11.1267. Min Act: -0.1700
Data Index: 2771599 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.6892. Min Range: -11.6892
Max Act: 11.0017. Min Act: -0.1700
Data Index: 4186926 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.6892. Min Range: -11.6892
Max Act: 10.9392. Min Act: -0.1700
Data Index: 7006219 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.6892. Min Range: -11.6892
Max Act: 11.0017. Min Act: -0.1700
Data Index: 7040667 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.6892. Min Range: -11.6892
Max Act: 10.9392. Min Act: -0.1700
Data Index: 7818155 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.6892. Min Range: -11.6892
Max Act: 10.8767. Min Act: -0.1700
Data Index: 1587501 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.6892. Min Range: -11.6892
Max Act: 10.8142. Min Act: -0.1700
Data Index: 3500381 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.6892. Min Range: -11.6892
Max Act: 10.9392. Min Act: -0.1700
Data Index: 646755 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.6892. Min Range: -11.6892
Max Act: 10.8142. Min Act: -0.1700
Data Index: 5348392 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.6892. Min Range: -11.6892
Max Act: 10.7517. Min Act: -0.1700
Data Index: 1729588 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.6892. Min Range: -11.6892
Max Act: 10.7517. Min Act: -0.1700
Data Index: 4570642 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.6892. Min Range: -11.6892
Max Act: 10.6892. Min Act: -0.1700
Data Index: 2938818 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.6892. Min Range: -11.6892
Max Act: 10.5642. Min Act: -0.1700
Data Index: 5486392 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.6892. Min Range: -11.6892
Max Act: 10.5642. Min Act: -0.1700
Data Index: 446389 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.6892. Min Range: -11.6892
Max Act: 10.5017. Min Act: -0.1700
Data Index: 4908059 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.6892. Min Range: -11.6892
Max Act: 10.4392. Min Act: -0.1700
Data Index: 7131921 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.6892. Min Range: -11.6892
Max Act: 10.4392. Min Act: -0.1700
Data Index: 7252118 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #19