Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 323 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0671. Min Range: -5.0671
Max Act: 5.0671. Min Act: -0.1700
Data Index: 931258 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0671. Min Range: -5.0671
Max Act: 5.0358. Min Act: -0.1700
Data Index: 312370 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0671. Min Range: -5.0671
Max Act: 4.9421. Min Act: -0.1700
Data Index: 1626411 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0671. Min Range: -5.0671
Max Act: 4.9108. Min Act: -0.1700
Data Index: 4677321 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0671. Min Range: -5.0671
Max Act: 4.9108. Min Act: -0.1700
Data Index: 8654822 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0671. Min Range: -5.0671
Max Act: 4.9108. Min Act: -0.1700
Data Index: 325231 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0671. Min Range: -5.0671
Max Act: 4.9108. Min Act: -0.1700
Data Index: 6863468 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0671. Min Range: -5.0671
Max Act: 4.8796. Min Act: -0.1700
Data Index: 2956523 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0671. Min Range: -5.0671
Max Act: 4.8796. Min Act: -0.1700
Data Index: 1447949 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0671. Min Range: -5.0671
Max Act: 4.8796. Min Act: -0.1700
Data Index: 3457635 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0671. Min Range: -5.0671
Max Act: 4.8483. Min Act: -0.1700
Data Index: 5215469 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0671. Min Range: -5.0671
Max Act: 4.7858. Min Act: -0.1700
Data Index: 856504 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0671. Min Range: -5.0671
Max Act: 4.7858. Min Act: -0.1700
Data Index: 8489900 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0671. Min Range: -5.0671
Max Act: 4.7858. Min Act: -0.1700
Data Index: 2490235 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0671. Min Range: -5.0671
Max Act: 4.7858. Min Act: -0.1700
Data Index: 3678650 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0671. Min Range: -5.0671
Max Act: 4.7858. Min Act: -0.1700
Data Index: 6915158 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0671. Min Range: -5.0671
Max Act: 4.7858. Min Act: -0.1700
Data Index: 7098644 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0671. Min Range: -5.0671
Max Act: 4.7858. Min Act: -0.1700
Data Index: 2844108 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0671. Min Range: -5.0671
Max Act: 4.7858. Min Act: -0.1700
Data Index: 7452399 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0671. Min Range: -5.0671
Max Act: 4.7858. Min Act: -0.1700
Data Index: 4308764 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19