Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2575 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.3962. Min Act: -0.1700
Data Index: 7341331 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.3337. Min Act: -0.1700
Data Index: 2137417 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.3024. Min Act: -0.1700
Data Index: 2360648 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.3024. Min Act: -0.1700
Data Index: 2248460 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.3024. Min Act: -0.1700
Data Index: 720851 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.2712. Min Act: -0.1700
Data Index: 233477 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.2399. Min Act: -0.1700
Data Index: 1054629 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.2712. Min Act: -0.1700
Data Index: 7477661 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.2399. Min Act: -0.1700
Data Index: 703975 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.2399. Min Act: -0.1700
Data Index: 4975137 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.2399. Min Act: -0.1700
Data Index: 7976230 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.2399. Min Act: -0.1700
Data Index: 3010986 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.2087. Min Act: -0.1700
Data Index: 4633922 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.2087. Min Act: -0.1700
Data Index: 5713315 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.2087. Min Act: -0.1700
Data Index: 6689172 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.2087. Min Act: -0.1700
Data Index: 3247707 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.2087. Min Act: -0.1700
Data Index: 2158987 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.1774. Min Act: -0.1700
Data Index: 5112850 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.1462. Min Act: -0.1700
Data Index: 1944241 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3962. Min Range: -4.3962
Max Act: 4.1774. Min Act: -0.1700
Data Index: 3535750 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19