Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2372 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8006. Min Range: -5.8006
Max Act: 5.8006. Min Act: -0.1700
Data Index: 1164738 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8006. Min Range: -5.8006
Max Act: 5.7069. Min Act: -0.1700
Data Index: 594493 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8006. Min Range: -5.8006
Max Act: 5.5506. Min Act: -0.1700
Data Index: 5068569 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8006. Min Range: -5.8006
Max Act: 5.4569. Min Act: -0.1700
Data Index: 8620747 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8006. Min Range: -5.8006
Max Act: 5.4256. Min Act: -0.1700
Data Index: 4048595 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8006. Min Range: -5.8006
Max Act: 5.4569. Min Act: -0.1700
Data Index: 1607597 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8006. Min Range: -5.8006
Max Act: 5.4256. Min Act: -0.1700
Data Index: 5444093 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8006. Min Range: -5.8006
Max Act: 5.4256. Min Act: -0.1700
Data Index: 2997840 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8006. Min Range: -5.8006
Max Act: 5.3319. Min Act: -0.1700
Data Index: 7045228 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8006. Min Range: -5.8006
Max Act: 5.3319. Min Act: -0.1700
Data Index: 5472037 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8006. Min Range: -5.8006
Max Act: 5.3319. Min Act: -0.1700
Data Index: 1295267 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8006. Min Range: -5.8006
Max Act: 5.3319. Min Act: -0.1700
Data Index: 6919277 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8006. Min Range: -5.8006
Max Act: 5.3319. Min Act: -0.1700
Data Index: 2677074 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8006. Min Range: -5.8006
Max Act: 5.3319. Min Act: -0.1700
Data Index: 216649 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8006. Min Range: -5.8006
Max Act: 5.3319. Min Act: -0.1700
Data Index: 2922964 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8006. Min Range: -5.8006
Max Act: 5.3006. Min Act: -0.1700
Data Index: 6660504 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8006. Min Range: -5.8006
Max Act: 5.3006. Min Act: -0.1700
Data Index: 1992837 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8006. Min Range: -5.8006
Max Act: 5.2694. Min Act: -0.1700
Data Index: 1151189 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8006. Min Range: -5.8006
Max Act: 5.3006. Min Act: -0.1700
Data Index: 738056 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8006. Min Range: -5.8006
Max Act: 5.3006. Min Act: -0.1700
Data Index: 2233269 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19