Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5632 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0543. Min Range: -6.0543
Max Act: 6.0543. Min Act: -0.1700
Data Index: 2372622 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0543. Min Range: -6.0543
Max Act: 6.0543. Min Act: -0.1700
Data Index: 7450997 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.9293. Min Act: -0.1700
Data Index: 1413716 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.8981. Min Act: -0.1700
Data Index: 2825514 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.8668. Min Act: -0.1700
Data Index: 6161203 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.8356. Min Act: -0.1700
Data Index: 2744791 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.8356. Min Act: -0.1700
Data Index: 5578437 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.8043. Min Act: -0.1700
Data Index: 6982696 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.7731. Min Act: -0.1700
Data Index: 7347204 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.7418. Min Act: -0.1700
Data Index: 8625320 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.7418. Min Act: -0.1700
Data Index: 69992 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.7418. Min Act: -0.1700
Data Index: 4422947 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.7418. Min Act: -0.1700
Data Index: 6827455 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.7106. Min Act: -0.1700
Data Index: 6208065 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.7106. Min Act: -0.1700
Data Index: 4925621 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.7106. Min Act: -0.1700
Data Index: 1248358 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.6793. Min Act: -0.1700
Data Index: 1066501 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.6793. Min Act: -0.1700
Data Index: 4143384 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.6793. Min Act: -0.1700
Data Index: 313107 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.6793. Min Act: -0.1700
Data Index: 8129326 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19