Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1893 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.1415. Min Range: -0.1415
Max Act: 0.1415. Min Act: -0.0001
Data Index: 993288 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1415. Min Range: -0.1415
Max Act: 0.1295. Min Act: -0.0001
Data Index: 1201675 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1415. Min Range: -0.1415
Max Act: 0.1221. Min Act: -0.0001
Data Index: 268298 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1415. Min Range: -0.1415
Max Act: 0.1154. Min Act: -0.0001
Data Index: 1638032 (Python Code)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1415. Min Range: -0.1415
Max Act: 0.1059. Min Act: -0.0001
Data Index: 255217 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1415. Min Range: -0.1415
Max Act: 0.1014. Min Act: -0.0001
Data Index: 568922 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1415. Min Range: -0.1415
Max Act: 0.1082. Min Act: -0.0001
Data Index: 1325243 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1415. Min Range: -0.1415
Max Act: 0.1061. Min Act: -0.0001
Data Index: 277260 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1415. Min Range: -0.1415
Max Act: 0.0955. Min Act: -0.0001
Data Index: 1277130 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1415. Min Range: -0.1415
Max Act: 0.1051. Min Act: -0.0001
Data Index: 435045 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1415. Min Range: -0.1415
Max Act: 0.0967. Min Act: -0.0001
Data Index: 1074204 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1415. Min Range: -0.1415
Max Act: 0.0992. Min Act: -0.0001
Data Index: 573785 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1415. Min Range: -0.1415
Max Act: 0.1018. Min Act: -0.0001
Data Index: 924727 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1415. Min Range: -0.1415
Max Act: 0.0983. Min Act: -0.0001
Data Index: 1066101 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1415. Min Range: -0.1415
Max Act: 0.0950. Min Act: -0.0001
Data Index: 884021 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1415. Min Range: -0.1415
Max Act: 0.0910. Min Act: -0.0001
Data Index: 1029807 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1415. Min Range: -0.1415
Max Act: 0.0970. Min Act: -0.0001
Data Index: 1193872 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1415. Min Range: -0.1415
Max Act: 0.0964. Min Act: -0.0001
Data Index: 1063911 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1415. Min Range: -0.1415
Max Act: 0.0988. Min Act: -0.0001
Data Index: 32385 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1415. Min Range: -0.1415
Max Act: 0.0992. Min Act: -0.0001
Data Index: 1609358 (Python Code)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19