Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2593 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.8921. Min Act: -0.1700
Data Index: 8521137 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.8609. Min Act: -0.1700
Data Index: 6839647 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.8609. Min Act: -0.1700
Data Index: 7271186 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.8609. Min Act: -0.1700
Data Index: 2500305 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.8296. Min Act: -0.1700
Data Index: 236337 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.8296. Min Act: -0.1700
Data Index: 643485 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.7983. Min Act: -0.1700
Data Index: 8781884 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.7827. Min Act: -0.1700
Data Index: 8075087 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.7827. Min Act: -0.1700
Data Index: 8781885 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.7514. Min Act: -0.1700
Data Index: 234050 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.7827. Min Act: -0.1700
Data Index: 8316902 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.7670. Min Act: -0.1700
Data Index: 236331 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.7670. Min Act: -0.1700
Data Index: 1216097 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.7670. Min Act: -0.1700
Data Index: 4836377 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.7514. Min Act: -0.1700
Data Index: 3902449 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.7514. Min Act: -0.1700
Data Index: 8659694 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.7514. Min Act: -0.1700
Data Index: 1253220 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.7358. Min Act: -0.1700
Data Index: 5857221 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.7514. Min Act: -0.1700
Data Index: 4757174 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.7514. Min Act: -0.1700
Data Index: 5961871 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #19