Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1575 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.2442. Min Range: -0.2442
Max Act: 0.2442. Min Act: -0.0001
Data Index: 1119237 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2442. Min Range: -0.2442
Max Act: 0.2038. Min Act: -0.0001
Data Index: 1176787 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2442. Min Range: -0.2442
Max Act: 0.2173. Min Act: -0.0001
Data Index: 975904 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2442. Min Range: -0.2442
Max Act: 0.1995. Min Act: -0.0001
Data Index: 604913 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2442. Min Range: -0.2442
Max Act: 0.1957. Min Act: -0.0001
Data Index: 805488 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2442. Min Range: -0.2442
Max Act: 0.2039. Min Act: -0.0001
Data Index: 629394 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2442. Min Range: -0.2442
Max Act: 0.2163. Min Act: -0.0001
Data Index: 52437 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2442. Min Range: -0.2442
Max Act: 0.1928. Min Act: -0.0001
Data Index: 1429793 (Python Code)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2442. Min Range: -0.2442
Max Act: 0.2026. Min Act: -0.0001
Data Index: 150266 (C4 (Web Text))
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2442. Min Range: -0.2442
Max Act: 0.1816. Min Act: -0.0001
Data Index: 84097 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2442. Min Range: -0.2442
Max Act: 0.2123. Min Act: -0.0001
Data Index: 492191 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2442. Min Range: -0.2442
Max Act: 0.2076. Min Act: -0.0001
Data Index: 157485 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2442. Min Range: -0.2442
Max Act: 0.1550. Min Act: -0.0001
Data Index: 847435 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2442. Min Range: -0.2442
Max Act: 0.1827. Min Act: -0.0001
Data Index: 353385 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2442. Min Range: -0.2442
Max Act: 0.1897. Min Act: -0.0001
Data Index: 106856 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2442. Min Range: -0.2442
Max Act: 0.1951. Min Act: -0.0001
Data Index: 1476936 (Python Code)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2442. Min Range: -0.2442
Max Act: 0.1661. Min Act: -0.0001
Data Index: 1115020 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2442. Min Range: -0.2442
Max Act: 0.1868. Min Act: -0.0001
Data Index: 412110 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2442. Min Range: -0.2442
Max Act: 0.1759. Min Act: -0.0001
Data Index: 553235 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2442. Min Range: -0.2442
Max Act: 0.1788. Min Act: -0.0001
Data Index: 1355765 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19