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

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

Neuron 4154 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: 4.0002. Min Range: -4.0002

Max Act: 3.7311. Min Act: -0.0001

Data Index: 1067056 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.7343. Min Act: -0.0001

Data Index: 333308 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 4.0002. Min Range: -4.0002

Max Act: 4.0002. Min Act: -0.0001

Data Index: 27179 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.7693. Min Act: -0.0001

Data Index: 770713 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.6455. Min Act: -0.0001

Data Index: 30095 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.3584. Min Act: -0.0001

Data Index: 64418 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.4481. Min Act: -0.0001

Data Index: 762879 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.7401. Min Act: -0.0001

Data Index: 522095 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.3852. Min Act: -0.0001

Data Index: 371731 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.3647. Min Act: -0.0001

Data Index: 990707 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.3589. Min Act: -0.0001

Data Index: 1335177 (C4 (Web Text))

Max Activating Token Index: 333

Text #11

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.2911. Min Act: -0.0001

Data Index: 889054 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.2849. Min Act: -0.0001

Data Index: 474727 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.4589. Min Act: -0.0001

Data Index: 1345129 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.2710. Min Act: -0.0001

Data Index: 1159939 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.4163. Min Act: -0.0001

Data Index: 315275 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.1210. Min Act: -0.0001

Data Index: 772215 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.2357. Min Act: -0.0001

Data Index: 47327 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.0974. Min Act: -0.0001

Data Index: 1354338 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.2267. Min Act: -0.0001

Data Index: 367948 (C4 (Web Text))

Max Activating Token Index: 397