Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2440 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.3220. Min Act: -0.0000

Data Index: 193967 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2930. Min Act: -0.0000

Data Index: 277669 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2544. Min Act: -0.0000

Data Index: 571902 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2793. Min Act: -0.0000

Data Index: 768398 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2585. Min Act: -0.0000

Data Index: 298839 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2276. Min Act: -0.0000

Data Index: 1225200 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.1807. Min Act: -0.0000

Data Index: 299213 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2213. Min Act: -0.0000

Data Index: 1285871 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.1885. Min Act: -0.0000

Data Index: 1317542 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2016. Min Act: -0.0000

Data Index: 789146 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.1887. Min Act: -0.0000

Data Index: 45826 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.1822. Min Act: -0.0000

Data Index: 464009 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.1690. Min Act: -0.0000

Data Index: 590594 (C4 (Web Text))

Max Activating Token Index: 630

Text #13

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.1942. Min Act: -0.0000

Data Index: 1079147 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.1883. Min Act: -0.0000

Data Index: 1286864 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.1757. Min Act: -0.0000

Data Index: 1034273 (C4 (Web Text))

Max Activating Token Index: 7

Text #16

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.1819. Min Act: -0.0000

Data Index: 1240649 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.1533. Min Act: -0.0000

Data Index: 46577 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.1668. Min Act: -0.0000

Data Index: 386118 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.1757. Min Act: -0.0000

Data Index: 818942 (C4 (Web Text))

Max Activating Token Index: 138