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

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

Neuron 3333 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: 0.3621. Min Range: -0.3621

Max Act: 0.3621. Min Act: -0.0001

Data Index: 825431 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2936. Min Act: -0.0001

Data Index: 588091 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2982. Min Act: -0.0001

Data Index: 1567574 (Python Code)

Max Activating Token Index: 445

Text #3

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3126. Min Act: -0.0001

Data Index: 1268403 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2766. Min Act: -0.0001

Data Index: 1153437 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2875. Min Act: -0.0001

Data Index: 176265 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2744. Min Act: -0.0000

Data Index: 402146 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2685. Min Act: -0.0000

Data Index: 538956 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2418. Min Act: -0.0000

Data Index: 906213 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2757. Min Act: -0.0001

Data Index: 1376902 (Python Code)

Max Activating Token Index: 990

Text #10

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2369. Min Act: -0.0001

Data Index: 391146 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2368. Min Act: -0.0001

Data Index: 1547470 (Python Code)

Max Activating Token Index: 163

Text #12

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2242. Min Act: -0.0001

Data Index: 1326807 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2172. Min Act: -0.0001

Data Index: 1386782 (Python Code)

Max Activating Token Index: 384

Text #14

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2416. Min Act: -0.0001

Data Index: 295588 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2132. Min Act: -0.0001

Data Index: 1090850 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2224. Min Act: -0.0000

Data Index: 138890 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2118. Min Act: -0.0001

Data Index: 1491629 (Python Code)

Max Activating Token Index: 37

Text #18

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2175. Min Act: -0.0000

Data Index: 1040258 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2039. Min Act: -0.0001

Data Index: 1455853 (Python Code)

Max Activating Token Index: 137