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

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

Neuron 1679 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: 0.3213. Min Range: -0.3213

Max Act: 0.3207. Min Act: -0.0000

Data Index: 1275955 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.3213. Min Act: -0.0000

Data Index: 1299876 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2940. Min Act: -0.0000

Data Index: 492911 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2811. Min Act: -0.0000

Data Index: 142179 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2842. Min Act: -0.0000

Data Index: 1395108 (Python Code)

Max Activating Token Index: 222

Text #5

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2548. Min Act: -0.0000

Data Index: 1528983 (Python Code)

Max Activating Token Index: 688

Text #6

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2499. Min Act: -0.0000

Data Index: 500373 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2777. Min Act: -0.0000

Data Index: 1613900 (Python Code)

Max Activating Token Index: 282

Text #8

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2355. Min Act: -0.0000

Data Index: 1062624 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2241. Min Act: -0.0000

Data Index: 80199 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2651. Min Act: -0.0000

Data Index: 1570344 (Python Code)

Max Activating Token Index: 622

Text #11

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2327. Min Act: -0.0000

Data Index: 1490665 (Python Code)

Max Activating Token Index: 398

Text #12

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2298. Min Act: -0.0000

Data Index: 1648687 (Python Code)

Max Activating Token Index: 691

Text #13

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2541. Min Act: -0.0000

Data Index: 784721 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2337. Min Act: -0.0000

Data Index: 172964 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2412. Min Act: -0.0000

Data Index: 1362208 (Python Code)

Max Activating Token Index: 608

Text #16

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2318. Min Act: -0.0000

Data Index: 1501035 (Python Code)

Max Activating Token Index: 724

Text #17

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2155. Min Act: -0.0000

Data Index: 906926 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2150. Min Act: -0.0000

Data Index: 1407146 (Python Code)

Max Activating Token Index: 175

Text #19

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2394. Min Act: -0.0000

Data Index: 1503660 (Python Code)

Max Activating Token Index: 197