Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 947 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5754. Min Range: -3.5754
Max Act: 3.5754. Min Act: -0.1700
Data Index: 7139180 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5754. Min Range: -3.5754
Max Act: 3.5284. Min Act: -0.1700
Data Index: 5922796 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5754. Min Range: -3.5754
Max Act: 3.3560. Min Act: -0.1700
Data Index: 7771534 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5754. Min Range: -3.5754
Max Act: 3.2619. Min Act: -0.1700
Data Index: 5983104 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5754. Min Range: -3.5754
Max Act: 3.2147. Min Act: -0.1700
Data Index: 3921400 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5754. Min Range: -3.5754
Max Act: 3.1833. Min Act: -0.1700
Data Index: 4310058 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5754. Min Range: -3.5754
Max Act: 3.1518. Min Act: -0.1700
Data Index: 1483139 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5754. Min Range: -3.5754
Max Act: 3.1045. Min Act: -0.1700
Data Index: 5731538 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5754. Min Range: -3.5754
Max Act: 3.1045. Min Act: -0.1700
Data Index: 33764 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5754. Min Range: -3.5754
Max Act: 3.1045. Min Act: -0.1700
Data Index: 4413341 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5754. Min Range: -3.5754
Max Act: 3.0888. Min Act: -0.1700
Data Index: 4932447 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5754. Min Range: -3.5754
Max Act: 3.0888. Min Act: -0.1700
Data Index: 2239490 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5754. Min Range: -3.5754
Max Act: 3.0730. Min Act: -0.1700
Data Index: 884608 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5754. Min Range: -3.5754
Max Act: 3.0730. Min Act: -0.1700
Data Index: 8397090 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5754. Min Range: -3.5754
Max Act: 3.0572. Min Act: -0.1700
Data Index: 8431530 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5754. Min Range: -3.5754
Max Act: 3.0414. Min Act: -0.1700
Data Index: 2241451 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5754. Min Range: -3.5754
Max Act: 3.0572. Min Act: -0.1700
Data Index: 4080923 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5754. Min Range: -3.5754
Max Act: 3.0414. Min Act: -0.1700
Data Index: 3302703 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5754. Min Range: -3.5754
Max Act: 3.0414. Min Act: -0.1700
Data Index: 2138074 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5754. Min Range: -3.5754
Max Act: 2.9941. Min Act: -0.1700
Data Index: 5058182 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19