Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1743 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.4817. Min Act: -0.1700
Data Index: 6152513 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.2942. Min Act: -0.1700
Data Index: 1335403 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.2629. Min Act: -0.1700
Data Index: 7165567 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.2317. Min Act: -0.1700
Data Index: 3646761 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.2629. Min Act: -0.1700
Data Index: 6682629 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.1379. Min Act: -0.1700
Data Index: 6667897 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.1379. Min Act: -0.1700
Data Index: 6736737 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.0442. Min Act: -0.1700
Data Index: 7856864 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.0754. Min Act: -0.1700
Data Index: 1482410 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.0442. Min Act: -0.1700
Data Index: 320647 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.0442. Min Act: -0.1700
Data Index: 621213 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.0442. Min Act: -0.1700
Data Index: 1482407 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.0442. Min Act: -0.1700
Data Index: 2347471 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.0442. Min Act: -0.1700
Data Index: 2164062 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.0129. Min Act: -0.1700
Data Index: 619819 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.0129. Min Act: -0.1700
Data Index: 6934454 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.0129. Min Act: -0.1700
Data Index: 8734726 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4817. Min Range: -5.4817
Max Act: 4.9817. Min Act: -0.1700
Data Index: 5558421 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.0129. Min Act: -0.1700
Data Index: 183893 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4817. Min Range: -5.4817
Max Act: 4.9817. Min Act: -0.1700
Data Index: 6501926 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19