Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1587 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7046. Min Range: -3.7046
Max Act: 3.7046. Min Act: -0.1700
Data Index: 5914367 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7046. Min Range: -3.7046
Max Act: 3.5168. Min Act: -0.1700
Data Index: 3274040 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7046. Min Range: -3.7046
Max Act: 3.4698. Min Act: -0.1700
Data Index: 5021451 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7046. Min Range: -3.7046
Max Act: 3.4385. Min Act: -0.1700
Data Index: 8592310 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7046. Min Range: -3.7046
Max Act: 3.4385. Min Act: -0.1700
Data Index: 3177698 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7046. Min Range: -3.7046
Max Act: 3.4228. Min Act: -0.1700
Data Index: 1989425 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7046. Min Range: -3.7046
Max Act: 3.4071. Min Act: -0.1700
Data Index: 4289843 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7046. Min Range: -3.7046
Max Act: 3.4071. Min Act: -0.1700
Data Index: 3041791 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7046. Min Range: -3.7046
Max Act: 3.3914. Min Act: -0.1700
Data Index: 52784 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7046. Min Range: -3.7046
Max Act: 3.3287. Min Act: -0.1700
Data Index: 4151129 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7046. Min Range: -3.7046
Max Act: 3.2973. Min Act: -0.1700
Data Index: 8188043 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7046. Min Range: -3.7046
Max Act: 3.3130. Min Act: -0.1700
Data Index: 2080491 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7046. Min Range: -3.7046
Max Act: 3.3130. Min Act: -0.1700
Data Index: 5271383 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7046. Min Range: -3.7046
Max Act: 3.2973. Min Act: -0.1700
Data Index: 5577621 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7046. Min Range: -3.7046
Max Act: 3.3130. Min Act: -0.1700
Data Index: 1669572 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7046. Min Range: -3.7046
Max Act: 3.2659. Min Act: -0.1700
Data Index: 8592311 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7046. Min Range: -3.7046
Max Act: 3.2816. Min Act: -0.1700
Data Index: 7354097 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7046. Min Range: -3.7046
Max Act: 3.2659. Min Act: -0.1700
Data Index: 3586878 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7046. Min Range: -3.7046
Max Act: 3.2659. Min Act: -0.1700
Data Index: 7145065 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7046. Min Range: -3.7046
Max Act: 3.2659. Min Act: -0.1700
Data Index: 4493448 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #19