Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6378 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6568. Min Range: -6.6568
Max Act: 6.6568. Min Act: -0.1700
Data Index: 2077626 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6568. Min Range: -6.6568
Max Act: 6.5943. Min Act: -0.1700
Data Index: 6827599 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6568. Min Range: -6.6568
Max Act: 6.4068. Min Act: -0.1700
Data Index: 5401561 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6568. Min Range: -6.6568
Max Act: 6.4693. Min Act: -0.1700
Data Index: 588947 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6568. Min Range: -6.6568
Max Act: 6.4068. Min Act: -0.1700
Data Index: 1055158 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6568. Min Range: -6.6568
Max Act: 6.3131. Min Act: -0.1700
Data Index: 3509349 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6568. Min Range: -6.6568
Max Act: 6.3131. Min Act: -0.1700
Data Index: 7476380 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6568. Min Range: -6.6568
Max Act: 6.2506. Min Act: -0.1700
Data Index: 5095498 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6568. Min Range: -6.6568
Max Act: 6.2506. Min Act: -0.1700
Data Index: 8633402 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6568. Min Range: -6.6568
Max Act: 6.2193. Min Act: -0.1700
Data Index: 2843512 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6568. Min Range: -6.6568
Max Act: 6.1568. Min Act: -0.1700
Data Index: 7294050 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6568. Min Range: -6.6568
Max Act: 6.1256. Min Act: -0.1700
Data Index: 6225232 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6568. Min Range: -6.6568
Max Act: 6.1568. Min Act: -0.1700
Data Index: 7854654 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6568. Min Range: -6.6568
Max Act: 6.1256. Min Act: -0.1700
Data Index: 596215 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6568. Min Range: -6.6568
Max Act: 6.1568. Min Act: -0.1700
Data Index: 5546173 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6568. Min Range: -6.6568
Max Act: 6.0318. Min Act: -0.1700
Data Index: 6167053 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6568. Min Range: -6.6568
Max Act: 6.0631. Min Act: -0.1700
Data Index: 797797 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6568. Min Range: -6.6568
Max Act: 6.0631. Min Act: -0.1700
Data Index: 5231974 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6568. Min Range: -6.6568
Max Act: 6.0631. Min Act: -0.1700
Data Index: 2982329 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6568. Min Range: -6.6568
Max Act: 6.0318. Min Act: -0.1700
Data Index: 330505 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19