Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 82 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.2361. Min Act: -0.0003

Data Index: 732997 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.2255. Min Act: -0.0003

Data Index: 836720 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.1971. Min Act: -0.0003

Data Index: 1047233 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.2127. Min Act: -0.0003

Data Index: 1114234 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.2439. Min Act: -0.0003

Data Index: 1203898 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.2494. Min Act: -0.0003

Data Index: 736299 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.2119. Min Act: -0.0003

Data Index: 597586 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.2172. Min Act: -0.0003

Data Index: 271836 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.2358. Min Act: -0.0003

Data Index: 908536 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.2273. Min Act: -0.0003

Data Index: 1094463 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.2046. Min Act: -0.0003

Data Index: 166653 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.1887. Min Act: -0.0003

Data Index: 744637 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.2292. Min Act: -0.0003

Data Index: 526145 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.2013. Min Act: -0.0003

Data Index: 1254672 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.2319. Min Act: -0.0003

Data Index: 174434 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.2121. Min Act: -0.0003

Data Index: 895998 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.1934. Min Act: -0.0003

Data Index: 713146 (C4 (Web Text))

Max Activating Token Index: 416

Text #17

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.2242. Min Act: -0.0003

Data Index: 870363 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.2168. Min Act: -0.0003

Data Index: 1349960 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.2158. Min Act: -0.0003

Data Index: 1257676 (C4 (Web Text))

Max Activating Token Index: 511