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

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

Neuron 1778 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2843. Min Act: -0.0000

Data Index: 451817 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2691. Min Act: -0.0000

Data Index: 1223935 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2498. Min Act: -0.0000

Data Index: 1352090 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2577. Min Act: -0.0000

Data Index: 5921 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2645. Min Act: -0.0000

Data Index: 124715 (C4 (Web Text))

Max Activating Token Index: 426

Text #5

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2337. Min Act: -0.0000

Data Index: 596170 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2528. Min Act: -0.0000

Data Index: 1073447 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2442. Min Act: -0.0000

Data Index: 573488 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2420. Min Act: -0.0000

Data Index: 246361 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2445. Min Act: -0.0000

Data Index: 368286 (C4 (Web Text))

Max Activating Token Index: 374

Text #10

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2329. Min Act: -0.0000

Data Index: 927040 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2296. Min Act: -0.0000

Data Index: 1256509 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2279. Min Act: -0.0000

Data Index: 243688 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2264. Min Act: -0.0000

Data Index: 706860 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2248. Min Act: -0.0000

Data Index: 1336100 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2271. Min Act: -0.0000

Data Index: 129779 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2118. Min Act: -0.0000

Data Index: 1186521 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2069. Min Act: -0.0000

Data Index: 924276 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2103. Min Act: -0.0000

Data Index: 291961 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.1942. Min Act: -0.0000

Data Index: 599934 (C4 (Web Text))

Max Activating Token Index: 754