Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1173 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.2294. Min Act: -0.0001

Data Index: 331329 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.2312. Min Act: -0.0001

Data Index: 1293821 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.2301. Min Act: -0.0001

Data Index: 567290 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.2208. Min Act: -0.0001

Data Index: 727122 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.2185. Min Act: -0.0000

Data Index: 916998 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.2164. Min Act: -0.0000

Data Index: 1307809 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.2145. Min Act: -0.0001

Data Index: 867184 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.2202. Min Act: -0.0001

Data Index: 1050585 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.2073. Min Act: -0.0001

Data Index: 1286038 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.2217. Min Act: -0.0001

Data Index: 1174851 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.2025. Min Act: -0.0001

Data Index: 820284 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.2116. Min Act: -0.0001

Data Index: 1346144 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.2110. Min Act: -0.0000

Data Index: 1077561 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1986. Min Act: -0.0001

Data Index: 1148555 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.2091. Min Act: -0.0001

Data Index: 548634 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.2143. Min Act: -0.0001

Data Index: 688669 (C4 (Web Text))

Max Activating Token Index: 7

Text #16

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.2145. Min Act: -0.0000

Data Index: 449064 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.2168. Min Act: -0.0000

Data Index: 245610 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.2069. Min Act: -0.0001

Data Index: 1143372 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1904. Min Act: -0.0001

Data Index: 828911 (C4 (Web Text))

Max Activating Token Index: 132