Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2894 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0961. Min Range: -2.0961
Max Act: 2.0961. Min Act: -0.1700
Data Index: 8618760 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0961. Min Range: -2.0961
Max Act: 2.0961. Min Act: -0.1700
Data Index: 8396084 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0961. Min Range: -2.0961
Max Act: 2.0289. Min Act: -0.1700
Data Index: 7683953 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0961. Min Range: -2.0961
Max Act: 2.0289. Min Act: -0.1700
Data Index: 3921581 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0961. Min Range: -2.0961
Max Act: 2.0289. Min Act: -0.1700
Data Index: 2083358 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0961. Min Range: -2.0961
Max Act: 2.0120. Min Act: -0.1700
Data Index: 5996188 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0961. Min Range: -2.0961
Max Act: 1.9951. Min Act: -0.1700
Data Index: 1279508 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0961. Min Range: -2.0961
Max Act: 1.9951. Min Act: -0.1700
Data Index: 2149208 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0961. Min Range: -2.0961
Max Act: 1.9782. Min Act: -0.1700
Data Index: 5142656 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0961. Min Range: -2.0961
Max Act: 1.9951. Min Act: -0.1700
Data Index: 2928839 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0961. Min Range: -2.0961
Max Act: 1.9443. Min Act: -0.1700
Data Index: 6743522 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0961. Min Range: -2.0961
Max Act: 1.9782. Min Act: -0.1700
Data Index: 3911134 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0961. Min Range: -2.0961
Max Act: 1.9612. Min Act: -0.1700
Data Index: 3048352 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0961. Min Range: -2.0961
Max Act: 1.9612. Min Act: -0.1700
Data Index: 4099804 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0961. Min Range: -2.0961
Max Act: 1.9612. Min Act: -0.1700
Data Index: 8797581 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0961. Min Range: -2.0961
Max Act: 1.9782. Min Act: -0.1700
Data Index: 5915769 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0961. Min Range: -2.0961
Max Act: 1.9612. Min Act: -0.1700
Data Index: 7532795 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0961. Min Range: -2.0961
Max Act: 1.9443. Min Act: -0.1700
Data Index: 7907596 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0961. Min Range: -2.0961
Max Act: 1.9443. Min Act: -0.1700
Data Index: 5531738 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0961. Min Range: -2.0961
Max Act: 1.9443. Min Act: -0.1700
Data Index: 585065 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19