Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5367 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0825. Min Range: -9.0825
Max Act: 9.0200. Min Act: -0.1700
Data Index: 2866610 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0825. Min Range: -9.0825
Max Act: 9.0825. Min Act: -0.1700
Data Index: 834430 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0825. Min Range: -9.0825
Max Act: 9.0200. Min Act: -0.1700
Data Index: 7766488 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0825. Min Range: -9.0825
Max Act: 9.0200. Min Act: -0.1700
Data Index: 5647017 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0825. Min Range: -9.0825
Max Act: 8.9575. Min Act: -0.1700
Data Index: 6039206 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0825. Min Range: -9.0825
Max Act: 9.0200. Min Act: -0.1700
Data Index: 6550234 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0825. Min Range: -9.0825
Max Act: 8.8950. Min Act: -0.1700
Data Index: 4466291 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0825. Min Range: -9.0825
Max Act: 8.8325. Min Act: -0.1700
Data Index: 2809111 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0825. Min Range: -9.0825
Max Act: 8.8325. Min Act: -0.1700
Data Index: 8730048 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0825. Min Range: -9.0825
Max Act: 8.7700. Min Act: -0.1700
Data Index: 2763315 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0825. Min Range: -9.0825
Max Act: 8.7700. Min Act: -0.1700
Data Index: 1201159 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0825. Min Range: -9.0825
Max Act: 8.7075. Min Act: -0.1700
Data Index: 3547173 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0825. Min Range: -9.0825
Max Act: 8.7075. Min Act: -0.1700
Data Index: 3739657 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0825. Min Range: -9.0825
Max Act: 8.7075. Min Act: -0.1700
Data Index: 8757559 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0825. Min Range: -9.0825
Max Act: 8.6450. Min Act: -0.1700
Data Index: 8272995 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0825. Min Range: -9.0825
Max Act: 8.5825. Min Act: -0.1700
Data Index: 2129641 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0825. Min Range: -9.0825
Max Act: 8.5825. Min Act: -0.1700
Data Index: 580096 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0825. Min Range: -9.0825
Max Act: 8.5200. Min Act: -0.1700
Data Index: 3306366 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0825. Min Range: -9.0825
Max Act: 8.5200. Min Act: -0.1700
Data Index: 2815333 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0825. Min Range: -9.0825
Max Act: 8.5200. Min Act: -0.1700
Data Index: 5283869 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19