Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3659 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1671. Min Range: -6.1671
Max Act: 6.1671. Min Act: -0.1700
Data Index: 211680 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1671. Min Range: -6.1671
Max Act: 6.0733. Min Act: -0.1700
Data Index: 5898967 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1671. Min Range: -6.1671
Max Act: 6.0108. Min Act: -0.1700
Data Index: 6123860 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1671. Min Range: -6.1671
Max Act: 6.0108. Min Act: -0.1700
Data Index: 1844138 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1671. Min Range: -6.1671
Max Act: 5.9796. Min Act: -0.1700
Data Index: 7884652 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1671. Min Range: -6.1671
Max Act: 5.9171. Min Act: -0.1700
Data Index: 553371 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1671. Min Range: -6.1671
Max Act: 5.9483. Min Act: -0.1700
Data Index: 6353183 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1671. Min Range: -6.1671
Max Act: 5.9483. Min Act: -0.1700
Data Index: 8468072 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1671. Min Range: -6.1671
Max Act: 5.9171. Min Act: -0.1700
Data Index: 3935023 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1671. Min Range: -6.1671
Max Act: 5.9483. Min Act: -0.1700
Data Index: 1801050 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1671. Min Range: -6.1671
Max Act: 5.8858. Min Act: -0.1700
Data Index: 611016 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1671. Min Range: -6.1671
Max Act: 5.8858. Min Act: -0.1700
Data Index: 3619272 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1671. Min Range: -6.1671
Max Act: 5.8546. Min Act: -0.1700
Data Index: 7916020 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1671. Min Range: -6.1671
Max Act: 5.8546. Min Act: -0.1700
Data Index: 636747 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1671. Min Range: -6.1671
Max Act: 5.8858. Min Act: -0.1700
Data Index: 3277471 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1671. Min Range: -6.1671
Max Act: 5.8546. Min Act: -0.1700
Data Index: 5325191 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1671. Min Range: -6.1671
Max Act: 5.8233. Min Act: -0.1700
Data Index: 3721390 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1671. Min Range: -6.1671
Max Act: 5.8233. Min Act: -0.1700
Data Index: 2615176 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1671. Min Range: -6.1671
Max Act: 5.8233. Min Act: -0.1700
Data Index: 1687628 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1671. Min Range: -6.1671
Max Act: 5.8233. Min Act: -0.1698
Data Index: 999609 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19