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

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

Neuron 373 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.3270. Min Act: -0.0001

Data Index: 1301538 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.3139. Min Act: -0.0001

Data Index: 1270362 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.2684. Min Act: -0.0001

Data Index: 430388 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.2902. Min Act: -0.0001

Data Index: 935057 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.3286. Min Act: -0.0001

Data Index: 134263 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.2441. Min Act: -0.0001

Data Index: 333198 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.2503. Min Act: -0.0001

Data Index: 978995 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.2644. Min Act: -0.0001

Data Index: 1209639 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.3289. Min Act: -0.0001

Data Index: 391097 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.2358. Min Act: -0.0001

Data Index: 1106959 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.2301. Min Act: -0.0001

Data Index: 549423 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.1859. Min Act: -0.0001

Data Index: 498053 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.2123. Min Act: -0.0001

Data Index: 321050 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.1657. Min Act: -0.0001

Data Index: 1221119 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.1248. Min Act: -0.0001

Data Index: 453306 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.1490. Min Act: -0.0001

Data Index: 461974 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.1353. Min Act: -0.0001

Data Index: 33131 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.0832. Min Act: -0.0001

Data Index: 759132 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.1318. Min Act: -0.0001

Data Index: 861957 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.0957. Min Act: -0.0001

Data Index: 356021 (C4 (Web Text))

Max Activating Token Index: 997