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

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

Neuron 3650 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2948. Min Act: -0.0001

Data Index: 1307923 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2507. Min Act: -0.0000

Data Index: 1032860 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2526. Min Act: -0.0001

Data Index: 320272 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2674. Min Act: -0.0001

Data Index: 887633 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2503. Min Act: -0.0001

Data Index: 182184 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2481. Min Act: -0.0001

Data Index: 582315 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2280. Min Act: -0.0001

Data Index: 353788 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2753. Min Act: -0.0001

Data Index: 1112418 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2365. Min Act: -0.0001

Data Index: 391943 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2301. Min Act: -0.0001

Data Index: 32402 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2451. Min Act: -0.0000

Data Index: 483708 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2383. Min Act: -0.0001

Data Index: 995968 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2226. Min Act: -0.0001

Data Index: 793998 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2180. Min Act: -0.0001

Data Index: 126014 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2135. Min Act: -0.0001

Data Index: 506057 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2458. Min Act: -0.0001

Data Index: 986158 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2279. Min Act: -0.0001

Data Index: 1082343 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2241. Min Act: -0.0001

Data Index: 247228 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2391. Min Act: -0.0001

Data Index: 1055654 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2202. Min Act: -0.0001

Data Index: 633746 (C4 (Web Text))

Max Activating Token Index: 600