Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5163 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4590. Min Range: -5.4590
Max Act: 5.4590. Min Act: -0.1700
Data Index: 2982624 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4590. Min Range: -5.4590
Max Act: 5.3965. Min Act: -0.1700
Data Index: 7021796 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4590. Min Range: -5.4590
Max Act: 5.2090. Min Act: -0.1700
Data Index: 8191217 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4590. Min Range: -5.4590
Max Act: 5.2090. Min Act: -0.1700
Data Index: 1501245 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4590. Min Range: -5.4590
Max Act: 5.2090. Min Act: -0.1700
Data Index: 4265178 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4590. Min Range: -5.4590
Max Act: 5.2403. Min Act: -0.1700
Data Index: 3636505 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4590. Min Range: -5.4590
Max Act: 5.1778. Min Act: -0.1700
Data Index: 1728443 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4590. Min Range: -5.4590
Max Act: 5.1465. Min Act: -0.1700
Data Index: 2072042 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4590. Min Range: -5.4590
Max Act: 5.0840. Min Act: -0.1700
Data Index: 4208504 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4590. Min Range: -5.4590
Max Act: 5.0840. Min Act: -0.1700
Data Index: 4206389 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4590. Min Range: -5.4590
Max Act: 5.0840. Min Act: -0.1700
Data Index: 4252595 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4590. Min Range: -5.4590
Max Act: 5.0840. Min Act: -0.1700
Data Index: 3973003 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4590. Min Range: -5.4590
Max Act: 5.0528. Min Act: -0.1700
Data Index: 1809978 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4590. Min Range: -5.4590
Max Act: 5.0528. Min Act: -0.1700
Data Index: 5249324 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4590. Min Range: -5.4590
Max Act: 5.0528. Min Act: -0.1700
Data Index: 3141708 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4590. Min Range: -5.4590
Max Act: 5.0528. Min Act: -0.1700
Data Index: 7476689 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4590. Min Range: -5.4590
Max Act: 5.0215. Min Act: -0.1700
Data Index: 1293812 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4590. Min Range: -5.4590
Max Act: 5.0215. Min Act: -0.1700
Data Index: 8609657 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4590. Min Range: -5.4590
Max Act: 5.0215. Min Act: -0.1700
Data Index: 247285 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4590. Min Range: -5.4590
Max Act: 5.0215. Min Act: -0.1700
Data Index: 4377243 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19