Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2179 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.3102. Min Range: -12.3102
Max Act: 12.3102. Min Act: -0.1700
Data Index: 5638866 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.3102. Min Range: -12.3102
Max Act: 11.9977. Min Act: -0.1700
Data Index: 5967607 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.3102. Min Range: -12.3102
Max Act: 11.7477. Min Act: -0.1700
Data Index: 5746065 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.3102. Min Range: -12.3102
Max Act: 11.7477. Min Act: -0.1700
Data Index: 7892221 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.3102. Min Range: -12.3102
Max Act: 11.6852. Min Act: -0.1700
Data Index: 7022804 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.3102. Min Range: -12.3102
Max Act: 11.6227. Min Act: -0.1700
Data Index: 7552918 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.3102. Min Range: -12.3102
Max Act: 11.6227. Min Act: -0.1700
Data Index: 3934731 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.3102. Min Range: -12.3102
Max Act: 11.4977. Min Act: -0.1700
Data Index: 1211439 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.3102. Min Range: -12.3102
Max Act: 11.4977. Min Act: -0.1700
Data Index: 2367511 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.3102. Min Range: -12.3102
Max Act: 11.4352. Min Act: -0.1700
Data Index: 1598458 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.3102. Min Range: -12.3102
Max Act: 11.4352. Min Act: -0.1700
Data Index: 8003200 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.3102. Min Range: -12.3102
Max Act: 11.4977. Min Act: -0.1700
Data Index: 450312 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.3102. Min Range: -12.3102
Max Act: 11.4352. Min Act: -0.1700
Data Index: 6325872 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.3102. Min Range: -12.3102
Max Act: 11.4352. Min Act: -0.1700
Data Index: 7377805 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.3102. Min Range: -12.3102
Max Act: 11.3727. Min Act: -0.1700
Data Index: 4418317 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.3102. Min Range: -12.3102
Max Act: 11.3727. Min Act: -0.1700
Data Index: 1217769 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.3102. Min Range: -12.3102
Max Act: 11.4352. Min Act: -0.1700
Data Index: 2971197 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.3102. Min Range: -12.3102
Max Act: 11.3102. Min Act: -0.1700
Data Index: 3635490 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.3102. Min Range: -12.3102
Max Act: 11.3102. Min Act: -0.1700
Data Index: 840122 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.3102. Min Range: -12.3102
Max Act: 11.3102. Min Act: -0.1700
Data Index: 4484143 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19