Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5228 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1694. Min Range: -5.1694
Max Act: 5.1694. Min Act: -0.1700
Data Index: 2945058 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1694. Min Range: -5.1694
Max Act: 5.1694. Min Act: -0.1698
Data Index: 1614545 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1694. Min Range: -5.1694
Max Act: 5.1382. Min Act: -0.1700
Data Index: 4374745 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1694. Min Range: -5.1694
Max Act: 5.1382. Min Act: -0.1700
Data Index: 7501683 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1694. Min Range: -5.1694
Max Act: 5.1069. Min Act: -0.1700
Data Index: 5015335 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1694. Min Range: -5.1694
Max Act: 5.1069. Min Act: -0.1700
Data Index: 3403576 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1694. Min Range: -5.1694
Max Act: 5.1069. Min Act: -0.1699
Data Index: 227479 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1694. Min Range: -5.1694
Max Act: 5.1069. Min Act: -0.1700
Data Index: 1822243 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1694. Min Range: -5.1694
Max Act: 5.1382. Min Act: -0.1700
Data Index: 2229417 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1694. Min Range: -5.1694
Max Act: 5.0757. Min Act: -0.1700
Data Index: 2728293 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1694. Min Range: -5.1694
Max Act: 5.0757. Min Act: -0.1696
Data Index: 4973742 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1694. Min Range: -5.1694
Max Act: 5.0757. Min Act: -0.1700
Data Index: 4969707 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1694. Min Range: -5.1694
Max Act: 5.0757. Min Act: -0.1700
Data Index: 1110153 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1694. Min Range: -5.1694
Max Act: 5.1069. Min Act: -0.1698
Data Index: 4196335 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1694. Min Range: -5.1694
Max Act: 5.0757. Min Act: -0.1689
Data Index: 2203894 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1694. Min Range: -5.1694
Max Act: 5.1069. Min Act: -0.1699
Data Index: 3946433 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1694. Min Range: -5.1694
Max Act: 5.0757. Min Act: -0.1700
Data Index: 448794 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1694. Min Range: -5.1694
Max Act: 5.0757. Min Act: -0.1689
Data Index: 3772404 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1694. Min Range: -5.1694
Max Act: 5.0757. Min Act: -0.1698
Data Index: 1761492 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1694. Min Range: -5.1694
Max Act: 5.0757. Min Act: -0.1700
Data Index: 611724 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19