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

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

Neuron 3886 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.3180. Min Act: -0.0000

Data Index: 240704 (C4 (Web Text))

Max Activating Token Index: 202

Text #1

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.3096. Min Act: -0.0000

Data Index: 1125020 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2853. Min Act: -0.0000

Data Index: 113154 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2654. Min Act: -0.0000

Data Index: 343660 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2640. Min Act: -0.0000

Data Index: 597580 (C4 (Web Text))

Max Activating Token Index: 366

Text #5

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2785. Min Act: -0.0000

Data Index: 162994 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2677. Min Act: -0.0000

Data Index: 578071 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2574. Min Act: -0.0000

Data Index: 289385 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2512. Min Act: -0.0000

Data Index: 77806 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2460. Min Act: -0.0000

Data Index: 90956 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2327. Min Act: -0.0000

Data Index: 1329308 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2445. Min Act: -0.0000

Data Index: 175225 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2275. Min Act: -0.0000

Data Index: 859397 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2179. Min Act: -0.0000

Data Index: 1235288 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2255. Min Act: 0.0000

Data Index: 163723 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2228. Min Act: -0.0000

Data Index: 1195967 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2217. Min Act: -0.0000

Data Index: 996302 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2281. Min Act: -0.0000

Data Index: 983705 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2218. Min Act: -0.0000

Data Index: 485450 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2223. Min Act: -0.0000

Data Index: 869742 (C4 (Web Text))

Max Activating Token Index: 701