Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1828 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8414. Min Range: -5.8414
Max Act: 5.8414. Min Act: -0.1700
Data Index: 6605518 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8414. Min Range: -5.8414
Max Act: 5.5289. Min Act: -0.1700
Data Index: 3410682 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8414. Min Range: -5.8414
Max Act: 5.4664. Min Act: -0.1700
Data Index: 6147238 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8414. Min Range: -5.8414
Max Act: 5.3101. Min Act: -0.1700
Data Index: 4836934 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8414. Min Range: -5.8414
Max Act: 5.3414. Min Act: -0.1700
Data Index: 7456992 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8414. Min Range: -5.8414
Max Act: 5.3414. Min Act: -0.1700
Data Index: 8174956 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8414. Min Range: -5.8414
Max Act: 5.2789. Min Act: -0.1700
Data Index: 3189229 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8414. Min Range: -5.8414
Max Act: 5.2789. Min Act: -0.1700
Data Index: 622249 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8414. Min Range: -5.8414
Max Act: 5.2789. Min Act: -0.1700
Data Index: 6218027 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8414. Min Range: -5.8414
Max Act: 5.2164. Min Act: -0.1700
Data Index: 7361010 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8414. Min Range: -5.8414
Max Act: 5.2164. Min Act: -0.1700
Data Index: 6932686 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8414. Min Range: -5.8414
Max Act: 5.1851. Min Act: -0.1700
Data Index: 950037 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8414. Min Range: -5.8414
Max Act: 5.1851. Min Act: -0.1700
Data Index: 3549031 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8414. Min Range: -5.8414
Max Act: 5.1539. Min Act: -0.1700
Data Index: 667933 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8414. Min Range: -5.8414
Max Act: 5.1851. Min Act: -0.1700
Data Index: 3206196 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8414. Min Range: -5.8414
Max Act: 5.1851. Min Act: -0.1700
Data Index: 2663326 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8414. Min Range: -5.8414
Max Act: 5.1539. Min Act: -0.1700
Data Index: 8507234 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8414. Min Range: -5.8414
Max Act: 5.2164. Min Act: -0.1700
Data Index: 7353532 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8414. Min Range: -5.8414
Max Act: 5.1539. Min Act: -0.1700
Data Index: 1483667 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8414. Min Range: -5.8414
Max Act: 5.1539. Min Act: -0.1700
Data Index: 3029388 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19