Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2790 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3357. Min Range: -6.3357
Max Act: 6.3357. Min Act: -0.1700
Data Index: 2326438 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3357. Min Range: -6.3357
Max Act: 6.2732. Min Act: -0.1700
Data Index: 708090 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3357. Min Range: -6.3357
Max Act: 6.1794. Min Act: -0.1700
Data Index: 3905765 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3357. Min Range: -6.3357
Max Act: 6.1794. Min Act: -0.1700
Data Index: 7060930 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3357. Min Range: -6.3357
Max Act: 6.1482. Min Act: -0.1700
Data Index: 7830236 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3357. Min Range: -6.3357
Max Act: 6.1482. Min Act: -0.1700
Data Index: 6252698 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3357. Min Range: -6.3357
Max Act: 6.0857. Min Act: -0.1700
Data Index: 3795124 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3357. Min Range: -6.3357
Max Act: 6.0544. Min Act: -0.1700
Data Index: 8178214 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3357. Min Range: -6.3357
Max Act: 6.0544. Min Act: -0.1700
Data Index: 7251015 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3357. Min Range: -6.3357
Max Act: 5.9919. Min Act: -0.1700
Data Index: 593607 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3357. Min Range: -6.3357
Max Act: 5.9919. Min Act: -0.1700
Data Index: 6657911 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3357. Min Range: -6.3357
Max Act: 5.9607. Min Act: -0.1700
Data Index: 4935326 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3357. Min Range: -6.3357
Max Act: 5.9607. Min Act: -0.1700
Data Index: 3830119 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3357. Min Range: -6.3357
Max Act: 5.9607. Min Act: -0.1700
Data Index: 2146623 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3357. Min Range: -6.3357
Max Act: 5.9607. Min Act: -0.1700
Data Index: 591406 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3357. Min Range: -6.3357
Max Act: 5.9607. Min Act: -0.1700
Data Index: 1783417 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3357. Min Range: -6.3357
Max Act: 5.9294. Min Act: -0.1700
Data Index: 5564629 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3357. Min Range: -6.3357
Max Act: 5.9294. Min Act: -0.1700
Data Index: 2545996 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3357. Min Range: -6.3357
Max Act: 5.9294. Min Act: -0.1700
Data Index: 320915 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3357. Min Range: -6.3357
Max Act: 5.9294. Min Act: -0.1700
Data Index: 7809286 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19