Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1253 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8278. Min Range: -5.8278
Max Act: 5.8278. Min Act: -0.1700
Data Index: 3132196 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8278. Min Range: -5.8278
Max Act: 5.6090. Min Act: -0.1700
Data Index: 6237829 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8278. Min Range: -5.8278
Max Act: 5.3590. Min Act: -0.1700
Data Index: 2648046 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8278. Min Range: -5.8278
Max Act: 5.3278. Min Act: -0.1700
Data Index: 4600050 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8278. Min Range: -5.8278
Max Act: 5.2653. Min Act: -0.1700
Data Index: 2942057 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8278. Min Range: -5.8278
Max Act: 5.2653. Min Act: -0.1700
Data Index: 3081968 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8278. Min Range: -5.8278
Max Act: 5.2340. Min Act: -0.1700
Data Index: 8312927 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8278. Min Range: -5.8278
Max Act: 5.2340. Min Act: -0.1700
Data Index: 6742453 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8278. Min Range: -5.8278
Max Act: 5.2340. Min Act: -0.1700
Data Index: 8312924 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8278. Min Range: -5.8278
Max Act: 5.2028. Min Act: -0.1700
Data Index: 2351881 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8278. Min Range: -5.8278
Max Act: 5.2028. Min Act: -0.1700
Data Index: 6668807 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8278. Min Range: -5.8278
Max Act: 5.2028. Min Act: -0.1700
Data Index: 997572 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8278. Min Range: -5.8278
Max Act: 5.1715. Min Act: -0.1700
Data Index: 4925252 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8278. Min Range: -5.8278
Max Act: 5.1403. Min Act: -0.1700
Data Index: 6798197 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8278. Min Range: -5.8278
Max Act: 5.1090. Min Act: -0.1700
Data Index: 7161214 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8278. Min Range: -5.8278
Max Act: 5.1403. Min Act: -0.1700
Data Index: 8312923 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8278. Min Range: -5.8278
Max Act: 5.1403. Min Act: -0.1700
Data Index: 3216264 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8278. Min Range: -5.8278
Max Act: 5.1403. Min Act: -0.1699
Data Index: 8216329 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8278. Min Range: -5.8278
Max Act: 5.1090. Min Act: -0.1700
Data Index: 7451323 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8278. Min Range: -5.8278
Max Act: 5.0778. Min Act: -0.1700
Data Index: 643558 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19