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

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

Neuron 5919 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1817. Min Act: -0.0000

Data Index: 832354 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1649. Min Act: -0.0000

Data Index: 1286140 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1364. Min Act: -0.0000

Data Index: 350950 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1380. Min Act: -0.0000

Data Index: 1059435 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1172. Min Act: -0.0000

Data Index: 1051668 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1046. Min Act: -0.0000

Data Index: 268708 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1160. Min Act: -0.0000

Data Index: 304249 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1135. Min Act: -0.0000

Data Index: 308507 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.0967. Min Act: -0.0000

Data Index: 18392 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1075. Min Act: -0.0000

Data Index: 789139 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1059. Min Act: -0.0000

Data Index: 1032547 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1143. Min Act: -0.0000

Data Index: 1299104 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1110. Min Act: -0.0000

Data Index: 1494086 (Python Code)

Max Activating Token Index: 910

Text #13

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1030. Min Act: -0.0000

Data Index: 1278136 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1018. Min Act: -0.0000

Data Index: 1035364 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.0975. Min Act: -0.0000

Data Index: 534977 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.0995. Min Act: -0.0000

Data Index: 1343664 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.0954. Min Act: -0.0000

Data Index: 1051040 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.0988. Min Act: -0.0000

Data Index: 1177677 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.0937. Min Act: -0.0000

Data Index: 220923 (C4 (Web Text))

Max Activating Token Index: 262