Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3010 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7483. Min Range: -5.7483
Max Act: 5.7483. Min Act: -0.1700
Data Index: 5994271 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7483. Min Range: -5.7483
Max Act: 5.6858. Min Act: -0.1700
Data Index: 5994272 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7483. Min Range: -5.7483
Max Act: 5.5295. Min Act: -0.1700
Data Index: 1242016 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7483. Min Range: -5.7483
Max Act: 5.3733. Min Act: -0.1700
Data Index: 2371882 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7483. Min Range: -5.7483
Max Act: 5.2795. Min Act: -0.1695
Data Index: 2353756 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7483. Min Range: -5.7483
Max Act: 5.1545. Min Act: -0.1700
Data Index: 5500882 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7483. Min Range: -5.7483
Max Act: 5.0920. Min Act: -0.1700
Data Index: 5885937 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7483. Min Range: -5.7483
Max Act: 5.0608. Min Act: -0.1700
Data Index: 3246356 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7483. Min Range: -5.7483
Max Act: 5.0608. Min Act: -0.1700
Data Index: 8368729 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7483. Min Range: -5.7483
Max Act: 5.0608. Min Act: -0.1700
Data Index: 5500874 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7483. Min Range: -5.7483
Max Act: 4.9983. Min Act: -0.1700
Data Index: 4526484 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7483. Min Range: -5.7483
Max Act: 4.9983. Min Act: -0.1700
Data Index: 8583946 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7483. Min Range: -5.7483
Max Act: 4.9983. Min Act: -0.1700
Data Index: 6530328 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7483. Min Range: -5.7483
Max Act: 4.9358. Min Act: -0.1700
Data Index: 7562466 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7483. Min Range: -5.7483
Max Act: 4.9358. Min Act: -0.1700
Data Index: 268769 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7483. Min Range: -5.7483
Max Act: 4.9358. Min Act: -0.1700
Data Index: 1242003 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7483. Min Range: -5.7483
Max Act: 4.9358. Min Act: -0.1700
Data Index: 3849278 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7483. Min Range: -5.7483
Max Act: 4.9045. Min Act: -0.1700
Data Index: 7935391 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7483. Min Range: -5.7483
Max Act: 4.9358. Min Act: -0.1700
Data Index: 498165 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7483. Min Range: -5.7483
Max Act: 4.9045. Min Act: -0.1700
Data Index: 5689423 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #19