Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3755 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3227. Min Range: -4.3227
Max Act: 4.3227. Min Act: -0.1700
Data Index: 3952736 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3227. Min Range: -4.3227
Max Act: 4.2601. Min Act: -0.1700
Data Index: 2660327 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3227. Min Range: -4.3227
Max Act: 4.2601. Min Act: -0.1700
Data Index: 4621094 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3227. Min Range: -4.3227
Max Act: 4.1351. Min Act: -0.1700
Data Index: 2171009 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3227. Min Range: -4.3227
Max Act: 4.1351. Min Act: -0.1700
Data Index: 646377 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3227. Min Range: -4.3227
Max Act: 4.1039. Min Act: -0.1700
Data Index: 4715491 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3227. Min Range: -4.3227
Max Act: 4.1039. Min Act: -0.1700
Data Index: 1230850 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3227. Min Range: -4.3227
Max Act: 4.1039. Min Act: -0.1700
Data Index: 6965599 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3227. Min Range: -4.3227
Max Act: 4.1039. Min Act: -0.1700
Data Index: 6016165 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3227. Min Range: -4.3227
Max Act: 4.0726. Min Act: -0.1700
Data Index: 539274 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3227. Min Range: -4.3227
Max Act: 4.1039. Min Act: -0.1700
Data Index: 5151131 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3227. Min Range: -4.3227
Max Act: 4.0726. Min Act: -0.1700
Data Index: 7258181 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3227. Min Range: -4.3227
Max Act: 4.0726. Min Act: -0.1700
Data Index: 3454450 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3227. Min Range: -4.3227
Max Act: 4.0414. Min Act: -0.1700
Data Index: 646381 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3227. Min Range: -4.3227
Max Act: 4.0414. Min Act: -0.1700
Data Index: 59034 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3227. Min Range: -4.3227
Max Act: 4.0726. Min Act: -0.1700
Data Index: 6839697 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3227. Min Range: -4.3227
Max Act: 4.0414. Min Act: -0.1700
Data Index: 5675782 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3227. Min Range: -4.3227
Max Act: 4.0414. Min Act: -0.1700
Data Index: 7246698 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3227. Min Range: -4.3227
Max Act: 3.9788. Min Act: -0.1700
Data Index: 2035840 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3227. Min Range: -4.3227
Max Act: 4.0101. Min Act: -0.1700
Data Index: 2159491 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19