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

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

Neuron 4899 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.3193. Min Act: -0.0000

Data Index: 1426765 (Python Code)

Max Activating Token Index: 323

Text #1

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2729. Min Act: -0.0000

Data Index: 1638669 (Python Code)

Max Activating Token Index: 814

Text #2

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2380. Min Act: -0.0000

Data Index: 1596368 (Python Code)

Max Activating Token Index: 562

Text #3

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2472. Min Act: -0.0000

Data Index: 878215 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2616. Min Act: -0.0000

Data Index: 1602358 (Python Code)

Max Activating Token Index: 202

Text #5

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2419. Min Act: -0.0000

Data Index: 1484204 (Python Code)

Max Activating Token Index: 792

Text #6

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2313. Min Act: -0.0000

Data Index: 1102914 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2364. Min Act: -0.0000

Data Index: 1438319 (Python Code)

Max Activating Token Index: 538

Text #8

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.0394. Min Act: -0.0000

Data Index: 438901 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2061. Min Act: -0.0000

Data Index: 1546024 (Python Code)

Max Activating Token Index: 770

Text #10

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2315. Min Act: -0.0000

Data Index: 1544330 (Python Code)

Max Activating Token Index: 70

Text #11

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2239. Min Act: -0.0000

Data Index: 1537246 (Python Code)

Max Activating Token Index: 634

Text #12

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2196. Min Act: -0.0000

Data Index: 654783 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2196. Min Act: -0.0000

Data Index: 1596735 (Python Code)

Max Activating Token Index: 987

Text #14

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2117. Min Act: -0.0000

Data Index: 1085924 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2232. Min Act: -0.0000

Data Index: 1634889 (Python Code)

Max Activating Token Index: 533

Text #16

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2177. Min Act: -0.0000

Data Index: 1524281 (Python Code)

Max Activating Token Index: 672

Text #17

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2162. Min Act: -0.0000

Data Index: 1623533 (Python Code)

Max Activating Token Index: 521

Text #18

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2054. Min Act: -0.0000

Data Index: 53532 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2032. Min Act: -0.0000

Data Index: 366491 (C4 (Web Text))

Max Activating Token Index: 1023