Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2524 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5483. Min Range: -6.5483
Max Act: 6.5483. Min Act: -0.1700
Data Index: 3598346 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5483. Min Range: -6.5483
Max Act: 6.2358. Min Act: -0.1700
Data Index: 2767702 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5483. Min Range: -6.5483
Max Act: 6.1421. Min Act: -0.1700
Data Index: 503002 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5483. Min Range: -6.5483
Max Act: 6.1108. Min Act: -0.1700
Data Index: 5461493 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5483. Min Range: -6.5483
Max Act: 6.0796. Min Act: -0.1700
Data Index: 5396939 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5483. Min Range: -6.5483
Max Act: 6.0483. Min Act: -0.1700
Data Index: 118255 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5483. Min Range: -6.5483
Max Act: 6.0483. Min Act: -0.1700
Data Index: 7510621 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5483. Min Range: -6.5483
Max Act: 5.9858. Min Act: -0.1700
Data Index: 1353774 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5483. Min Range: -6.5483
Max Act: 5.9546. Min Act: -0.1700
Data Index: 7451737 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5483. Min Range: -6.5483
Max Act: 5.9233. Min Act: -0.1700
Data Index: 2054919 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5483. Min Range: -6.5483
Max Act: 5.9233. Min Act: -0.1700
Data Index: 350119 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5483. Min Range: -6.5483
Max Act: 5.9233. Min Act: -0.1700
Data Index: 5647206 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5483. Min Range: -6.5483
Max Act: 5.8921. Min Act: -0.1700
Data Index: 4235143 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5483. Min Range: -6.5483
Max Act: 5.8296. Min Act: -0.1700
Data Index: 7948678 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5483. Min Range: -6.5483
Max Act: 5.8296. Min Act: -0.1700
Data Index: 1776281 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5483. Min Range: -6.5483
Max Act: 5.8296. Min Act: -0.1700
Data Index: 2659636 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5483. Min Range: -6.5483
Max Act: 5.7983. Min Act: -0.1700
Data Index: 6268685 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5483. Min Range: -6.5483
Max Act: 5.8296. Min Act: -0.1700
Data Index: 6809810 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5483. Min Range: -6.5483
Max Act: 5.8296. Min Act: -0.1700
Data Index: 7003903 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5483. Min Range: -6.5483
Max Act: 5.7983. Min Act: -0.1700
Data Index: 6075855 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19