Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4764 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0236. Min Range: -6.0236
Max Act: 6.0236. Min Act: -0.1700
Data Index: 7313146 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0236. Min Range: -6.0236
Max Act: 5.9924. Min Act: -0.1700
Data Index: 7930961 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0236. Min Range: -6.0236
Max Act: 5.9299. Min Act: -0.1700
Data Index: 4111047 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0236. Min Range: -6.0236
Max Act: 5.8986. Min Act: -0.1700
Data Index: 7569742 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0236. Min Range: -6.0236
Max Act: 5.8674. Min Act: -0.1700
Data Index: 3946671 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0236. Min Range: -6.0236
Max Act: 5.8674. Min Act: -0.1700
Data Index: 3724481 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0236. Min Range: -6.0236
Max Act: 5.8049. Min Act: -0.1700
Data Index: 2108497 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0236. Min Range: -6.0236
Max Act: 5.7736. Min Act: -0.1700
Data Index: 4146258 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0236. Min Range: -6.0236
Max Act: 5.7424. Min Act: -0.1700
Data Index: 1838812 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0236. Min Range: -6.0236
Max Act: 5.7424. Min Act: -0.1700
Data Index: 8026487 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0236. Min Range: -6.0236
Max Act: 5.7424. Min Act: -0.1700
Data Index: 5819 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0236. Min Range: -6.0236
Max Act: 5.7111. Min Act: -0.1700
Data Index: 4926457 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0236. Min Range: -6.0236
Max Act: 5.7111. Min Act: -0.1700
Data Index: 5170422 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0236. Min Range: -6.0236
Max Act: 5.6799. Min Act: -0.1700
Data Index: 314366 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0236. Min Range: -6.0236
Max Act: 5.6486. Min Act: -0.1700
Data Index: 721461 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0236. Min Range: -6.0236
Max Act: 5.6486. Min Act: -0.1700
Data Index: 4861689 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0236. Min Range: -6.0236
Max Act: 5.6486. Min Act: -0.1700
Data Index: 6670722 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0236. Min Range: -6.0236
Max Act: 5.6486. Min Act: -0.1700
Data Index: 4412670 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0236. Min Range: -6.0236
Max Act: 5.6799. Min Act: -0.1700
Data Index: 6391822 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0236. Min Range: -6.0236
Max Act: 5.6486. Min Act: -0.1700
Data Index: 3171816 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19