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

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

Neuron 4886 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0431. Min Range: -3.0431

Max Act: 3.0431. Min Act: -0.0001

Data Index: 1267920 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 3.0431. Min Range: -3.0431

Max Act: 2.8304. Min Act: -0.0001

Data Index: 1208542 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 3.0431. Min Range: -3.0431

Max Act: 2.8777. Min Act: -0.0001

Data Index: 254188 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 3.0431. Min Range: -3.0431

Max Act: 2.6676. Min Act: -0.0001

Data Index: 180324 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 3.0431. Min Range: -3.0431

Max Act: 2.5317. Min Act: -0.0001

Data Index: 68741 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 3.0431. Min Range: -3.0431

Max Act: 2.2325. Min Act: -0.0001

Data Index: 1214611 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 3.0431. Min Range: -3.0431

Max Act: 2.3305. Min Act: -0.0001

Data Index: 151775 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 3.0431. Min Range: -3.0431

Max Act: 2.1723. Min Act: -0.0001

Data Index: 412267 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 3.0431. Min Range: -3.0431

Max Act: 2.2943. Min Act: -0.0001

Data Index: 515480 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 3.0431. Min Range: -3.0431

Max Act: 2.4031. Min Act: -0.0001

Data Index: 1213230 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 3.0431. Min Range: -3.0431

Max Act: 2.0765. Min Act: -0.0001

Data Index: 212631 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 3.0431. Min Range: -3.0431

Max Act: 2.0577. Min Act: -0.0001

Data Index: 523392 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 3.0431. Min Range: -3.0431

Max Act: 2.1156. Min Act: -0.0001

Data Index: 292114 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 3.0431. Min Range: -3.0431

Max Act: 2.1634. Min Act: -0.0001

Data Index: 847488 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 3.0431. Min Range: -3.0431

Max Act: 2.2748. Min Act: -0.0001

Data Index: 591212 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 3.0431. Min Range: -3.0431

Max Act: 2.2088. Min Act: -0.0001

Data Index: 1327768 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 3.0431. Min Range: -3.0431

Max Act: 2.0044. Min Act: -0.0001

Data Index: 1089528 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 3.0431. Min Range: -3.0431

Max Act: 1.9569. Min Act: -0.0001

Data Index: 1357091 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 3.0431. Min Range: -3.0431

Max Act: 2.0916. Min Act: -0.0001

Data Index: 227479 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 3.0431. Min Range: -3.0431

Max Act: 1.9757. Min Act: -0.0001

Data Index: 828426 (C4 (Web Text))

Max Activating Token Index: 825