Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 499 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0202. Min Range: -6.0202
Max Act: 6.0202. Min Act: -0.1700
Data Index: 6478649 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.9890. Min Act: -0.1700
Data Index: 6363729 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.9890. Min Act: -0.1700
Data Index: 3373765 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.9265. Min Act: -0.1700
Data Index: 6487996 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.8640. Min Act: -0.1700
Data Index: 7972283 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.7390. Min Act: -0.1700
Data Index: 6099877 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.8015. Min Act: -0.1700
Data Index: 2078555 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.7390. Min Act: -0.1700
Data Index: 6720243 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.6765. Min Act: -0.1700
Data Index: 3668738 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.7390. Min Act: -0.1700
Data Index: 8355858 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.7077. Min Act: -0.1700
Data Index: 4557444 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.6765. Min Act: -0.1700
Data Index: 2040141 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.6765. Min Act: -0.1700
Data Index: 7460320 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.6452. Min Act: -0.1700
Data Index: 4167675 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.6452. Min Act: -0.1700
Data Index: 2205113 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.6452. Min Act: -0.1700
Data Index: 3662195 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.6140. Min Act: -0.1700
Data Index: 3844582 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.6140. Min Act: -0.1700
Data Index: 7613287 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.6140. Min Act: -0.1700
Data Index: 7613285 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.5827. Min Act: -0.1700
Data Index: 958980 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19