Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2050 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8017. Min Range: -8.8017
Max Act: 8.8017. Min Act: -0.1700
Data Index: 8610069 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8017. Min Range: -8.8017
Max Act: 8.7392. Min Act: -0.1700
Data Index: 7153239 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8017. Min Range: -8.8017
Max Act: 8.4892. Min Act: -0.1700
Data Index: 4311638 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8017. Min Range: -8.8017
Max Act: 8.4892. Min Act: -0.1700
Data Index: 7241317 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8017. Min Range: -8.8017
Max Act: 8.4267. Min Act: -0.1700
Data Index: 4430529 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8017. Min Range: -8.8017
Max Act: 8.4267. Min Act: -0.1700
Data Index: 5012402 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8017. Min Range: -8.8017
Max Act: 8.3642. Min Act: -0.1700
Data Index: 7353393 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8017. Min Range: -8.8017
Max Act: 8.3642. Min Act: -0.1700
Data Index: 4272233 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8017. Min Range: -8.8017
Max Act: 8.3642. Min Act: -0.1700
Data Index: 2500223 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8017. Min Range: -8.8017
Max Act: 8.3017. Min Act: -0.1700
Data Index: 7709086 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8017. Min Range: -8.8017
Max Act: 8.2705. Min Act: -0.1700
Data Index: 5046867 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8017. Min Range: -8.8017
Max Act: 8.2705. Min Act: -0.1700
Data Index: 678467 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8017. Min Range: -8.8017
Max Act: 8.2705. Min Act: -0.1700
Data Index: 3288173 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8017. Min Range: -8.8017
Max Act: 8.2392. Min Act: -0.1700
Data Index: 725414 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8017. Min Range: -8.8017
Max Act: 8.2392. Min Act: -0.1700
Data Index: 5970205 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8017. Min Range: -8.8017
Max Act: 8.2392. Min Act: -0.1700
Data Index: 7008478 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8017. Min Range: -8.8017
Max Act: 8.2080. Min Act: -0.1700
Data Index: 5252828 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8017. Min Range: -8.8017
Max Act: 8.1767. Min Act: -0.1700
Data Index: 725418 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8017. Min Range: -8.8017
Max Act: 8.1455. Min Act: -0.1700
Data Index: 828367 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8017. Min Range: -8.8017
Max Act: 8.1455. Min Act: -0.1700
Data Index: 8214862 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19