Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2587 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8372. Min Range: -5.8372
Max Act: 5.8372. Min Act: -0.1700
Data Index: 5087414 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8372. Min Range: -5.8372
Max Act: 5.8372. Min Act: -0.1700
Data Index: 2349467 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8372. Min Range: -5.8372
Max Act: 5.7747. Min Act: -0.1700
Data Index: 3731801 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8372. Min Range: -5.8372
Max Act: 5.7435. Min Act: -0.1700
Data Index: 3896100 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8372. Min Range: -5.8372
Max Act: 5.7122. Min Act: -0.1700
Data Index: 219966 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8372. Min Range: -5.8372
Max Act: 5.7747. Min Act: -0.1700
Data Index: 1801981 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8372. Min Range: -5.8372
Max Act: 5.7435. Min Act: -0.1700
Data Index: 1925023 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8372. Min Range: -5.8372
Max Act: 5.7122. Min Act: -0.1700
Data Index: 5415535 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8372. Min Range: -5.8372
Max Act: 5.7435. Min Act: -0.1700
Data Index: 1716952 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8372. Min Range: -5.8372
Max Act: 5.7122. Min Act: -0.1700
Data Index: 2512431 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8372. Min Range: -5.8372
Max Act: 5.7122. Min Act: -0.1700
Data Index: 4935150 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8372. Min Range: -5.8372
Max Act: 5.6810. Min Act: -0.1700
Data Index: 1831893 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8372. Min Range: -5.8372
Max Act: 5.6810. Min Act: -0.1700
Data Index: 3564015 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8372. Min Range: -5.8372
Max Act: 5.6497. Min Act: -0.1700
Data Index: 7971512 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8372. Min Range: -5.8372
Max Act: 5.6497. Min Act: -0.1700
Data Index: 5119543 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8372. Min Range: -5.8372
Max Act: 5.6497. Min Act: -0.1700
Data Index: 4565225 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8372. Min Range: -5.8372
Max Act: 5.6497. Min Act: -0.1700
Data Index: 601631 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8372. Min Range: -5.8372
Max Act: 5.6497. Min Act: -0.1700
Data Index: 6536234 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8372. Min Range: -5.8372
Max Act: 5.6497. Min Act: -0.1700
Data Index: 1063625 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8372. Min Range: -5.8372
Max Act: 5.6810. Min Act: -0.1700
Data Index: 2015753 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19