Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1623 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4602. Min Range: -6.4602
Max Act: 6.4602. Min Act: -0.1700
Data Index: 6028459 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4602. Min Range: -6.4602
Max Act: 6.4602. Min Act: -0.1700
Data Index: 5713316 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4602. Min Range: -6.4602
Max Act: 6.3977. Min Act: -0.1700
Data Index: 8068794 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4602. Min Range: -6.4602
Max Act: 6.3039. Min Act: -0.1700
Data Index: 4985029 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4602. Min Range: -6.4602
Max Act: 6.3039. Min Act: -0.1700
Data Index: 4855090 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4602. Min Range: -6.4602
Max Act: 6.2727. Min Act: -0.1700
Data Index: 2398167 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4602. Min Range: -6.4602
Max Act: 6.2727. Min Act: -0.1700
Data Index: 5909856 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4602. Min Range: -6.4602
Max Act: 6.2727. Min Act: -0.1700
Data Index: 1763874 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4602. Min Range: -6.4602
Max Act: 6.2414. Min Act: -0.1700
Data Index: 7453131 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4602. Min Range: -6.4602
Max Act: 6.2102. Min Act: -0.1700
Data Index: 5814852 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4602. Min Range: -6.4602
Max Act: 6.2102. Min Act: -0.1700
Data Index: 753401 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4602. Min Range: -6.4602
Max Act: 6.2102. Min Act: -0.1700
Data Index: 4433417 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4602. Min Range: -6.4602
Max Act: 6.2102. Min Act: -0.1700
Data Index: 7637247 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4602. Min Range: -6.4602
Max Act: 6.1789. Min Act: -0.1700
Data Index: 4912326 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4602. Min Range: -6.4602
Max Act: 6.1789. Min Act: -0.1700
Data Index: 4221467 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4602. Min Range: -6.4602
Max Act: 6.1789. Min Act: -0.1700
Data Index: 4518080 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4602. Min Range: -6.4602
Max Act: 6.1789. Min Act: -0.1700
Data Index: 3172756 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4602. Min Range: -6.4602
Max Act: 6.1789. Min Act: -0.1700
Data Index: 5527553 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4602. Min Range: -6.4602
Max Act: 6.1477. Min Act: -0.1700
Data Index: 3819228 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4602. Min Range: -6.4602
Max Act: 6.1164. Min Act: -0.1700
Data Index: 5943172 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19