Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2856 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7367. Min Range: -5.7367
Max Act: 5.7367. Min Act: -0.1700
Data Index: 5085130 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7367. Min Range: -5.7367
Max Act: 5.7055. Min Act: -0.1700
Data Index: 3661627 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7367. Min Range: -5.7367
Max Act: 5.6742. Min Act: -0.1700
Data Index: 6193274 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7367. Min Range: -5.7367
Max Act: 5.5492. Min Act: -0.1700
Data Index: 534551 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7367. Min Range: -5.7367
Max Act: 5.5180. Min Act: -0.1700
Data Index: 290498 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7367. Min Range: -5.7367
Max Act: 5.5180. Min Act: -0.1700
Data Index: 4543431 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7367. Min Range: -5.7367
Max Act: 5.5180. Min Act: -0.1700
Data Index: 1022034 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7367. Min Range: -5.7367
Max Act: 5.4867. Min Act: -0.1700
Data Index: 7686160 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7367. Min Range: -5.7367
Max Act: 5.4867. Min Act: -0.1700
Data Index: 5661377 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7367. Min Range: -5.7367
Max Act: 5.4867. Min Act: -0.1700
Data Index: 4733178 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7367. Min Range: -5.7367
Max Act: 5.4242. Min Act: -0.1700
Data Index: 4733179 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7367. Min Range: -5.7367
Max Act: 5.3930. Min Act: -0.1700
Data Index: 115438 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7367. Min Range: -5.7367
Max Act: 5.3930. Min Act: -0.1700
Data Index: 6665271 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7367. Min Range: -5.7367
Max Act: 5.3930. Min Act: -0.1700
Data Index: 1608628 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7367. Min Range: -5.7367
Max Act: 5.3617. Min Act: -0.1700
Data Index: 268390 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7367. Min Range: -5.7367
Max Act: 5.3305. Min Act: -0.1700
Data Index: 2970151 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7367. Min Range: -5.7367
Max Act: 5.3305. Min Act: -0.1700
Data Index: 4735466 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7367. Min Range: -5.7367
Max Act: 5.2992. Min Act: -0.1700
Data Index: 7178429 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7367. Min Range: -5.7367
Max Act: 5.2992. Min Act: -0.1700
Data Index: 4882524 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7367. Min Range: -5.7367
Max Act: 5.2367. Min Act: -0.1700
Data Index: 5851527 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19