Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4422 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2539. Min Range: -7.2539
Max Act: 7.2539. Min Act: -0.1700
Data Index: 2682932 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2539. Min Range: -7.2539
Max Act: 7.2539. Min Act: -0.1700
Data Index: 2810926 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2539. Min Range: -7.2539
Max Act: 7.2226. Min Act: -0.1700
Data Index: 6071137 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2539. Min Range: -7.2539
Max Act: 7.2539. Min Act: -0.1700
Data Index: 7773123 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2539. Min Range: -7.2539
Max Act: 7.1914. Min Act: -0.1700
Data Index: 5652633 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2539. Min Range: -7.2539
Max Act: 7.1601. Min Act: -0.1700
Data Index: 8164533 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2539. Min Range: -7.2539
Max Act: 7.1289. Min Act: -0.1700
Data Index: 1825833 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2539. Min Range: -7.2539
Max Act: 7.1289. Min Act: -0.1700
Data Index: 3253075 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2539. Min Range: -7.2539
Max Act: 7.1289. Min Act: -0.1700
Data Index: 5894828 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2539. Min Range: -7.2539
Max Act: 7.1601. Min Act: -0.1700
Data Index: 2256952 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2539. Min Range: -7.2539
Max Act: 7.1289. Min Act: -0.1700
Data Index: 867164 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2539. Min Range: -7.2539
Max Act: 7.0664. Min Act: -0.1700
Data Index: 7543233 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2539. Min Range: -7.2539
Max Act: 7.0976. Min Act: -0.1700
Data Index: 2198526 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2539. Min Range: -7.2539
Max Act: 7.0664. Min Act: -0.1700
Data Index: 1149369 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2539. Min Range: -7.2539
Max Act: 7.0976. Min Act: -0.1700
Data Index: 4223138 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2539. Min Range: -7.2539
Max Act: 7.0976. Min Act: -0.1700
Data Index: 1859395 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2539. Min Range: -7.2539
Max Act: 7.0664. Min Act: -0.1700
Data Index: 2325426 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2539. Min Range: -7.2539
Max Act: 7.0664. Min Act: -0.1700
Data Index: 7189698 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2539. Min Range: -7.2539
Max Act: 7.0351. Min Act: -0.1700
Data Index: 1379760 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2539. Min Range: -7.2539
Max Act: 7.0351. Min Act: -0.1700
Data Index: 6304007 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19