Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 118 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.3542. Min Act: -0.0000

Data Index: 160070 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.3212. Min Act: -0.0000

Data Index: 1052797 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.3055. Min Act: -0.0000

Data Index: 997492 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.2896. Min Act: -0.0000

Data Index: 328567 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.2701. Min Act: -0.0000

Data Index: 823721 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.2817. Min Act: -0.0000

Data Index: 170625 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.2789. Min Act: 0.0000

Data Index: 92428 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.2611. Min Act: -0.0000

Data Index: 694500 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.2475. Min Act: -0.0000

Data Index: 46437 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.2535. Min Act: -0.0000

Data Index: 308154 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.2355. Min Act: 0.0000

Data Index: 386545 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.2339. Min Act: -0.0000

Data Index: 1282756 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.2251. Min Act: -0.0000

Data Index: 820133 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.2446. Min Act: -0.0000

Data Index: 856169 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.2260. Min Act: -0.0000

Data Index: 185463 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.2250. Min Act: 0.0000

Data Index: 1347308 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.2242. Min Act: -0.0000

Data Index: 1284546 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.2226. Min Act: -0.0000

Data Index: 83659 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.2209. Min Act: -0.0000

Data Index: 332827 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.2169. Min Act: -0.0000

Data Index: 106469 (C4 (Web Text))

Max Activating Token Index: 411