Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2853 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0712. Min Range: -6.0712
Max Act: 6.0712. Min Act: -0.1700
Data Index: 2881000 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0712. Min Range: -6.0712
Max Act: 5.9150. Min Act: -0.1700
Data Index: 2969157 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0712. Min Range: -6.0712
Max Act: 5.7900. Min Act: -0.1700
Data Index: 5326581 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0712. Min Range: -6.0712
Max Act: 5.8212. Min Act: -0.1700
Data Index: 8008362 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0712. Min Range: -6.0712
Max Act: 5.7587. Min Act: -0.1700
Data Index: 8340367 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0712. Min Range: -6.0712
Max Act: 5.7275. Min Act: -0.1700
Data Index: 2357694 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0712. Min Range: -6.0712
Max Act: 5.6962. Min Act: -0.1700
Data Index: 3741134 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0712. Min Range: -6.0712
Max Act: 5.6650. Min Act: -0.1700
Data Index: 2135625 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0712. Min Range: -6.0712
Max Act: 5.6337. Min Act: -0.1700
Data Index: 2266345 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0712. Min Range: -6.0712
Max Act: 5.6337. Min Act: -0.1700
Data Index: 7098379 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0712. Min Range: -6.0712
Max Act: 5.6337. Min Act: -0.1700
Data Index: 7944747 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0712. Min Range: -6.0712
Max Act: 5.5712. Min Act: -0.1700
Data Index: 3466969 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0712. Min Range: -6.0712
Max Act: 5.5400. Min Act: -0.1700
Data Index: 3078727 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0712. Min Range: -6.0712
Max Act: 5.5712. Min Act: -0.1700
Data Index: 1600888 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0712. Min Range: -6.0712
Max Act: 5.5712. Min Act: -0.1700
Data Index: 1180997 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0712. Min Range: -6.0712
Max Act: 5.5400. Min Act: -0.1700
Data Index: 6637723 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0712. Min Range: -6.0712
Max Act: 5.5400. Min Act: -0.1700
Data Index: 3329408 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0712. Min Range: -6.0712
Max Act: 5.5087. Min Act: -0.1700
Data Index: 4937456 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0712. Min Range: -6.0712
Max Act: 5.5400. Min Act: -0.1700
Data Index: 3893436 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0712. Min Range: -6.0712
Max Act: 5.5087. Min Act: -0.1700
Data Index: 1472892 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19