Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3573 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4822. Min Range: -6.4822
Max Act: 6.4822. Min Act: -0.1700
Data Index: 4596836 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4822. Min Range: -6.4822
Max Act: 6.2947. Min Act: -0.1700
Data Index: 5873664 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4822. Min Range: -6.4822
Max Act: 6.2010. Min Act: -0.1700
Data Index: 3462408 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4822. Min Range: -6.4822
Max Act: 5.8885. Min Act: -0.1700
Data Index: 500213 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4822. Min Range: -6.4822
Max Act: 5.8260. Min Act: -0.1700
Data Index: 1219581 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4822. Min Range: -6.4822
Max Act: 5.7947. Min Act: -0.1700
Data Index: 6669014 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4822. Min Range: -6.4822
Max Act: 5.7635. Min Act: -0.1700
Data Index: 7192696 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4822. Min Range: -6.4822
Max Act: 5.7322. Min Act: -0.1700
Data Index: 7790874 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4822. Min Range: -6.4822
Max Act: 5.7322. Min Act: -0.1700
Data Index: 1013607 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4822. Min Range: -6.4822
Max Act: 5.7322. Min Act: -0.1700
Data Index: 6027440 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4822. Min Range: -6.4822
Max Act: 5.7322. Min Act: -0.1700
Data Index: 1479198 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4822. Min Range: -6.4822
Max Act: 5.7010. Min Act: -0.1700
Data Index: 2397542 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4822. Min Range: -6.4822
Max Act: 5.7010. Min Act: -0.1700
Data Index: 2834837 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4822. Min Range: -6.4822
Max Act: 5.7010. Min Act: -0.1700
Data Index: 3435259 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4822. Min Range: -6.4822
Max Act: 5.6697. Min Act: -0.1700
Data Index: 2095101 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4822. Min Range: -6.4822
Max Act: 5.6697. Min Act: -0.1700
Data Index: 6110464 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4822. Min Range: -6.4822
Max Act: 5.6697. Min Act: -0.1700
Data Index: 5818800 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4822. Min Range: -6.4822
Max Act: 5.7010. Min Act: -0.1700
Data Index: 1308282 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4822. Min Range: -6.4822
Max Act: 5.6385. Min Act: -0.1700
Data Index: 5430615 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4822. Min Range: -6.4822
Max Act: 5.6697. Min Act: -0.1700
Data Index: 3088400 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19