Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3544 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1556. Min Range: -6.1556
Max Act: 6.1556. Min Act: -0.1700
Data Index: 1613727 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1556. Min Range: -6.1556
Max Act: 6.0931. Min Act: -0.1700
Data Index: 3954966 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1556. Min Range: -6.1556
Max Act: 6.0306. Min Act: -0.1700
Data Index: 5213051 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1556. Min Range: -6.1556
Max Act: 6.0306. Min Act: -0.1700
Data Index: 3205041 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1556. Min Range: -6.1556
Max Act: 6.0306. Min Act: -0.1700
Data Index: 2786414 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1556. Min Range: -6.1556
Max Act: 5.9681. Min Act: -0.1700
Data Index: 2062470 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1556. Min Range: -6.1556
Max Act: 5.9681. Min Act: -0.1700
Data Index: 56055 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1556. Min Range: -6.1556
Max Act: 5.9681. Min Act: -0.1700
Data Index: 7694894 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1556. Min Range: -6.1556
Max Act: 5.9681. Min Act: -0.1700
Data Index: 6783689 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1556. Min Range: -6.1556
Max Act: 5.9369. Min Act: -0.1700
Data Index: 5383103 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1556. Min Range: -6.1556
Max Act: 5.9369. Min Act: -0.1700
Data Index: 4280561 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1556. Min Range: -6.1556
Max Act: 5.9056. Min Act: -0.1700
Data Index: 157512 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1556. Min Range: -6.1556
Max Act: 5.9056. Min Act: -0.1700
Data Index: 6114573 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1556. Min Range: -6.1556
Max Act: 5.9056. Min Act: -0.1700
Data Index: 6552957 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1556. Min Range: -6.1556
Max Act: 5.8744. Min Act: -0.1700
Data Index: 6351344 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1556. Min Range: -6.1556
Max Act: 5.8431. Min Act: -0.1700
Data Index: 3557047 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1556. Min Range: -6.1556
Max Act: 5.8431. Min Act: -0.1700
Data Index: 3152693 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1556. Min Range: -6.1556
Max Act: 5.8431. Min Act: -0.1700
Data Index: 8128651 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1556. Min Range: -6.1556
Max Act: 5.8119. Min Act: -0.1700
Data Index: 5160501 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1556. Min Range: -6.1556
Max Act: 5.8431. Min Act: -0.1700
Data Index: 7997548 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19