Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2370 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.4533. Min Range: -1.4533
Max Act: 1.4533. Min Act: -0.0001
Data Index: 709719 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4533. Min Range: -1.4533
Max Act: 1.3148. Min Act: -0.0001
Data Index: 13167 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4533. Min Range: -1.4533
Max Act: 1.3227. Min Act: -0.0001
Data Index: 697669 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4533. Min Range: -1.4533
Max Act: 1.2249. Min Act: -0.0001
Data Index: 430682 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4533. Min Range: -1.4533
Max Act: 1.2804. Min Act: -0.0001
Data Index: 677617 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4533. Min Range: -1.4533
Max Act: 1.1761. Min Act: -0.0001
Data Index: 653064 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4533. Min Range: -1.4533
Max Act: 1.3602. Min Act: -0.0001
Data Index: 986965 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4533. Min Range: -1.4533
Max Act: 1.4029. Min Act: -0.0001
Data Index: 627514 (C4 (Web Text))
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4533. Min Range: -1.4533
Max Act: 1.2081. Min Act: -0.0001
Data Index: 214121 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4533. Min Range: -1.4533
Max Act: 1.2565. Min Act: -0.0001
Data Index: 864315 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4533. Min Range: -1.4533
Max Act: 1.2198. Min Act: -0.0001
Data Index: 445247 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4533. Min Range: -1.4533
Max Act: 1.2936. Min Act: -0.0001
Data Index: 1157673 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4533. Min Range: -1.4533
Max Act: 1.2132. Min Act: -0.0001
Data Index: 224680 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4533. Min Range: -1.4533
Max Act: 1.2404. Min Act: -0.0001
Data Index: 38166 (C4 (Web Text))
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4533. Min Range: -1.4533
Max Act: 1.1347. Min Act: -0.0001
Data Index: 231509 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4533. Min Range: -1.4533
Max Act: 1.0682. Min Act: -0.0001
Data Index: 1314714 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4533. Min Range: -1.4533
Max Act: 1.1185. Min Act: -0.0001
Data Index: 1245824 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4533. Min Range: -1.4533
Max Act: 1.1566. Min Act: -0.0001
Data Index: 1043677 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4533. Min Range: -1.4533
Max Act: 1.0688. Min Act: -0.0001
Data Index: 902213 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4533. Min Range: -1.4533
Max Act: 1.0957. Min Act: -0.0001
Data Index: 267110 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19