Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3431 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.8887. Min Act: -0.1700
Data Index: 8256056 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.6700. Min Act: -0.1700
Data Index: 7265476 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.6387. Min Act: -0.1700
Data Index: 4877879 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.6075. Min Act: -0.1700
Data Index: 5983272 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.5762. Min Act: -0.1700
Data Index: 1830890 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.5450. Min Act: -0.1700
Data Index: 1953855 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.5137. Min Act: -0.1700
Data Index: 4761034 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.4825. Min Act: -0.1700
Data Index: 2271546 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.4200. Min Act: -0.1700
Data Index: 4338612 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.4512. Min Act: -0.1700
Data Index: 7712846 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.4512. Min Act: -0.1700
Data Index: 6521680 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.4200. Min Act: -0.1700
Data Index: 4623987 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.3887. Min Act: -0.1700
Data Index: 7813520 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.3887. Min Act: -0.1700
Data Index: 2582908 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.3575. Min Act: -0.1700
Data Index: 3405422 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.3575. Min Act: -0.1700
Data Index: 2679203 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.3262. Min Act: -0.1700
Data Index: 895657 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.3575. Min Act: -0.1700
Data Index: 3955774 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.3262. Min Act: -0.1700
Data Index: 310661 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.2950. Min Act: -0.1700
Data Index: 2208396 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19