Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4629 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6789. Min Range: -3.6789
Max Act: 3.6633. Min Act: -0.1700
Data Index: 3246136 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6789. Min Range: -3.6789
Max Act: 3.6789. Min Act: -0.1700
Data Index: 8739750 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6789. Min Range: -3.6789
Max Act: 3.6476. Min Act: -0.1700
Data Index: 5034239 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6789. Min Range: -3.6789
Max Act: 3.6476. Min Act: -0.1700
Data Index: 7154390 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6789. Min Range: -3.6789
Max Act: 3.6320. Min Act: -0.1700
Data Index: 8179245 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6789. Min Range: -3.6789
Max Act: 3.6320. Min Act: -0.1700
Data Index: 3956226 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6789. Min Range: -3.6789
Max Act: 3.6007. Min Act: -0.1700
Data Index: 4309063 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6789. Min Range: -3.6789
Max Act: 3.6007. Min Act: -0.1700
Data Index: 1710306 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6789. Min Range: -3.6789
Max Act: 3.6007. Min Act: -0.1700
Data Index: 52150 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6789. Min Range: -3.6789
Max Act: 3.5694. Min Act: -0.1700
Data Index: 6991239 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6789. Min Range: -3.6789
Max Act: 3.5381. Min Act: -0.1700
Data Index: 4734521 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6789. Min Range: -3.6789
Max Act: 3.5381. Min Act: -0.1700
Data Index: 7397118 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6789. Min Range: -3.6789
Max Act: 3.5381. Min Act: -0.1700
Data Index: 2564923 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6789. Min Range: -3.6789
Max Act: 3.5381. Min Act: -0.1700
Data Index: 817401 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6789. Min Range: -3.6789
Max Act: 3.5224. Min Act: -0.1700
Data Index: 6507310 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6789. Min Range: -3.6789
Max Act: 3.5224. Min Act: -0.1700
Data Index: 7695614 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6789. Min Range: -3.6789
Max Act: 3.4754. Min Act: -0.1700
Data Index: 7044170 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6789. Min Range: -3.6789
Max Act: 3.5067. Min Act: -0.1700
Data Index: 4727296 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6789. Min Range: -3.6789
Max Act: 3.4911. Min Act: -0.1700
Data Index: 2313451 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6789. Min Range: -3.6789
Max Act: 3.4754. Min Act: -0.1700
Data Index: 4245898 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19