Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4586 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0101. Min Range: -5.0101
Max Act: 5.0101. Min Act: -0.1700
Data Index: 5528028 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0101. Min Range: -5.0101
Max Act: 4.7914. Min Act: -0.1700
Data Index: 166821 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0101. Min Range: -5.0101
Max Act: 4.7289. Min Act: -0.1700
Data Index: 5135319 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0101. Min Range: -5.0101
Max Act: 4.6976. Min Act: -0.1700
Data Index: 5818142 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0101. Min Range: -5.0101
Max Act: 4.6976. Min Act: -0.1700
Data Index: 6358691 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0101. Min Range: -5.0101
Max Act: 4.6976. Min Act: -0.1700
Data Index: 510180 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0101. Min Range: -5.0101
Max Act: 4.6664. Min Act: -0.1700
Data Index: 6261744 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0101. Min Range: -5.0101
Max Act: 4.6664. Min Act: -0.1700
Data Index: 343319 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0101. Min Range: -5.0101
Max Act: 4.6664. Min Act: -0.1700
Data Index: 4524826 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0101. Min Range: -5.0101
Max Act: 4.6664. Min Act: -0.1700
Data Index: 2818570 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0101. Min Range: -5.0101
Max Act: 4.6351. Min Act: -0.1700
Data Index: 1523662 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0101. Min Range: -5.0101
Max Act: 4.6351. Min Act: -0.1700
Data Index: 2625092 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0101. Min Range: -5.0101
Max Act: 4.6351. Min Act: -0.1700
Data Index: 2834115 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0101. Min Range: -5.0101
Max Act: 4.6039. Min Act: -0.1700
Data Index: 1618407 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0101. Min Range: -5.0101
Max Act: 4.6351. Min Act: -0.1700
Data Index: 6052581 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0101. Min Range: -5.0101
Max Act: 4.6351. Min Act: -0.1700
Data Index: 1903536 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0101. Min Range: -5.0101
Max Act: 4.6351. Min Act: -0.1700
Data Index: 7225806 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0101. Min Range: -5.0101
Max Act: 4.6351. Min Act: -0.1700
Data Index: 7606054 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0101. Min Range: -5.0101
Max Act: 4.6351. Min Act: -0.1700
Data Index: 4771257 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0101. Min Range: -5.0101
Max Act: 4.6351. Min Act: -0.1700
Data Index: 7999686 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19