Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4639 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6054. Min Range: -4.6054
Max Act: 4.6054. Min Act: -0.1700
Data Index: 8196446 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6054. Min Range: -4.6054
Max Act: 4.5429. Min Act: -0.1700
Data Index: 482436 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6054. Min Range: -4.6054
Max Act: 4.5117. Min Act: -0.1700
Data Index: 1328110 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6054. Min Range: -4.6054
Max Act: 4.5429. Min Act: -0.1700
Data Index: 2686296 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6054. Min Range: -4.6054
Max Act: 4.4804. Min Act: -0.1700
Data Index: 1328121 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6054. Min Range: -4.6054
Max Act: 4.4492. Min Act: -0.1700
Data Index: 881307 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6054. Min Range: -4.6054
Max Act: 4.4492. Min Act: -0.1700
Data Index: 582281 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6054. Min Range: -4.6054
Max Act: 4.4179. Min Act: -0.1700
Data Index: 6813315 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6054. Min Range: -4.6054
Max Act: 4.4179. Min Act: -0.1700
Data Index: 8196448 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6054. Min Range: -4.6054
Max Act: 4.3554. Min Act: -0.1700
Data Index: 5531749 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6054. Min Range: -4.6054
Max Act: 4.3867. Min Act: -0.1700
Data Index: 6050247 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6054. Min Range: -4.6054
Max Act: 4.3554. Min Act: -0.1700
Data Index: 881299 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6054. Min Range: -4.6054
Max Act: 4.3554. Min Act: -0.1700
Data Index: 8797592 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6054. Min Range: -4.6054
Max Act: 4.3554. Min Act: -0.1700
Data Index: 5981030 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6054. Min Range: -4.6054
Max Act: 4.3554. Min Act: -0.1700
Data Index: 6188308 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6054. Min Range: -4.6054
Max Act: 4.3242. Min Act: -0.1700
Data Index: 8196447 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6054. Min Range: -4.6054
Max Act: 4.3242. Min Act: -0.1700
Data Index: 2582529 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6054. Min Range: -4.6054
Max Act: 4.3242. Min Act: -0.1700
Data Index: 8305132 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6054. Min Range: -4.6054
Max Act: 4.3242. Min Act: -0.1700
Data Index: 1328123 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6054. Min Range: -4.6054
Max Act: 4.3242. Min Act: -0.1700
Data Index: 6924774 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19