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

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

Neuron 375 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.5523. Min Act: -0.0000

Data Index: 1150939 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.5462. Min Act: -0.0000

Data Index: 565360 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.5079. Min Act: -0.0000

Data Index: 596940 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.5202. Min Act: -0.0000

Data Index: 1091951 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4914. Min Act: -0.0000

Data Index: 1120878 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4616. Min Act: -0.0000

Data Index: 1204395 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4707. Min Act: -0.0000

Data Index: 547007 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4516. Min Act: -0.0000

Data Index: 825508 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4630. Min Act: -0.0000

Data Index: 1214380 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4626. Min Act: -0.0000

Data Index: 470777 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4580. Min Act: -0.0000

Data Index: 954189 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4350. Min Act: -0.0000

Data Index: 496499 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4459. Min Act: -0.0000

Data Index: 1240472 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4291. Min Act: -0.0000

Data Index: 332796 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4263. Min Act: -0.0000

Data Index: 853799 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4152. Min Act: -0.0000

Data Index: 108323 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4310. Min Act: -0.0000

Data Index: 1136673 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4164. Min Act: 0.0000

Data Index: 1252704 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4098. Min Act: -0.0000

Data Index: 372107 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4496. Min Act: -0.0000

Data Index: 432127 (C4 (Web Text))

Max Activating Token Index: 360