Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3092 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2290. Min Range: -1.2290

Max Act: 1.2290. Min Act: -0.0000

Data Index: 279073 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 1.2290. Min Range: -1.2290

Max Act: 1.0873. Min Act: -0.0000

Data Index: 334052 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 1.2290. Min Range: -1.2290

Max Act: 1.1587. Min Act: -0.0000

Data Index: 1103908 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 1.2290. Min Range: -1.2290

Max Act: 1.1450. Min Act: -0.0000

Data Index: 133075 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 1.2290. Min Range: -1.2290

Max Act: 1.1031. Min Act: -0.0000

Data Index: 929994 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 1.2290. Min Range: -1.2290

Max Act: 1.1668. Min Act: -0.0000

Data Index: 77479 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 1.2290. Min Range: -1.2290

Max Act: 1.0114. Min Act: -0.0000

Data Index: 779239 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 1.2290. Min Range: -1.2290

Max Act: 1.1210. Min Act: -0.0000

Data Index: 1448054 (Python Code)

Max Activating Token Index: 908

Text #8

Max Range: 1.2290. Min Range: -1.2290

Max Act: 1.0273. Min Act: -0.0000

Data Index: 52125 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 1.2290. Min Range: -1.2290

Max Act: 1.0007. Min Act: -0.0000

Data Index: 936215 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 1.2290. Min Range: -1.2290

Max Act: 0.9712. Min Act: -0.0000

Data Index: 594281 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 1.2290. Min Range: -1.2290

Max Act: 1.0353. Min Act: -0.0000

Data Index: 269844 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 1.2290. Min Range: -1.2290

Max Act: 0.9069. Min Act: -0.0000

Data Index: 229467 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 1.2290. Min Range: -1.2290

Max Act: 1.0175. Min Act: -0.0000

Data Index: 667916 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 1.2290. Min Range: -1.2290

Max Act: 0.9809. Min Act: -0.0000

Data Index: 519335 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 1.2290. Min Range: -1.2290

Max Act: 1.0703. Min Act: -0.0000

Data Index: 665581 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 1.2290. Min Range: -1.2290

Max Act: 0.9383. Min Act: -0.0000

Data Index: 966333 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 1.2290. Min Range: -1.2290

Max Act: 0.9645. Min Act: -0.0000

Data Index: 264494 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 1.2290. Min Range: -1.2290

Max Act: 0.9512. Min Act: -0.0000

Data Index: 708469 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 1.2290. Min Range: -1.2290

Max Act: 0.9192. Min Act: -0.0000

Data Index: 532616 (C4 (Web Text))

Max Activating Token Index: 493