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

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

Neuron 3667 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.3269. Min Act: -0.0003

Data Index: 22395 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2748. Min Act: -0.0003

Data Index: 18065 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2743. Min Act: -0.0003

Data Index: 1185894 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2470. Min Act: -0.0003

Data Index: 603960 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2592. Min Act: -0.0003

Data Index: 1584585 (Python Code)

Max Activating Token Index: 598

Text #5

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2566. Min Act: -0.0003

Data Index: 824920 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2328. Min Act: -0.0003

Data Index: 176178 (C4 (Web Text))

Max Activating Token Index: 572

Text #7

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2489. Min Act: -0.0003

Data Index: 991802 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2455. Min Act: -0.0003

Data Index: 806319 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2627. Min Act: -0.0003

Data Index: 284411 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2436. Min Act: -0.0003

Data Index: 1306831 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2229. Min Act: -0.0003

Data Index: 376953 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2377. Min Act: -0.0003

Data Index: 809835 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2341. Min Act: -0.0003

Data Index: 297967 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2311. Min Act: -0.0002

Data Index: 1455255 (Python Code)

Max Activating Token Index: 966

Text #15

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2168. Min Act: -0.0003

Data Index: 231490 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2245. Min Act: -0.0002

Data Index: 1607893 (Python Code)

Max Activating Token Index: 715

Text #17

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2405. Min Act: -0.0002

Data Index: 1461 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2404. Min Act: -0.0003

Data Index: 134243 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2236. Min Act: -0.0003

Data Index: 727711 (C4 (Web Text))

Max Activating Token Index: 423