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

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

Neuron 5799 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2614. Min Act: -0.0000

Data Index: 1445189 (Python Code)

Max Activating Token Index: 929

Text #1

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2711. Min Act: -0.0000

Data Index: 1528366 (Python Code)

Max Activating Token Index: 549

Text #2

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2560. Min Act: -0.0000

Data Index: 1430167 (Python Code)

Max Activating Token Index: 646

Text #3

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2436. Min Act: -0.0000

Data Index: 1523913 (Python Code)

Max Activating Token Index: 848

Text #4

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2390. Min Act: -0.0000

Data Index: 1475589 (Python Code)

Max Activating Token Index: 858

Text #5

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2382. Min Act: -0.0000

Data Index: 228278 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2344. Min Act: -0.0000

Data Index: 1636579 (Python Code)

Max Activating Token Index: 964

Text #7

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2326. Min Act: -0.0000

Data Index: 577700 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2214. Min Act: -0.0001

Data Index: 1584845 (Python Code)

Max Activating Token Index: 270

Text #9

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2341. Min Act: -0.0000

Data Index: 734241 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2165. Min Act: -0.0000

Data Index: 1406040 (Python Code)

Max Activating Token Index: 136

Text #11

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2164. Min Act: -0.0000

Data Index: 515530 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2230. Min Act: -0.0001

Data Index: 1572970 (Python Code)

Max Activating Token Index: 757

Text #13

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2231. Min Act: -0.0000

Data Index: 1360014 (Python Code)

Max Activating Token Index: 108

Text #14

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2075. Min Act: -0.0000

Data Index: 1362081 (Python Code)

Max Activating Token Index: 157

Text #15

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2221. Min Act: -0.0000

Data Index: 1618650 (Python Code)

Max Activating Token Index: 63

Text #16

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2040. Min Act: -0.0000

Data Index: 1623569 (Python Code)

Max Activating Token Index: 317

Text #17

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.1970. Min Act: -0.0001

Data Index: 998894 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2095. Min Act: -0.0000

Data Index: 1421364 (Python Code)

Max Activating Token Index: 254

Text #19

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2032. Min Act: -0.0000

Data Index: 938232 (C4 (Web Text))

Max Activating Token Index: 116