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

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

Neuron 1579 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1195. Min Act: -0.0001

Data Index: 410758 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1282. Min Act: -0.0001

Data Index: 885409 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1189. Min Act: -0.0001

Data Index: 520928 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1233. Min Act: -0.0001

Data Index: 305661 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1104. Min Act: -0.0001

Data Index: 49670 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1021. Min Act: -0.0001

Data Index: 1201025 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1175. Min Act: -0.0001

Data Index: 1144064 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1160. Min Act: -0.0001

Data Index: 1049376 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1078. Min Act: -0.0001

Data Index: 145229 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.0943. Min Act: -0.0001

Data Index: 918110 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.0926. Min Act: -0.0001

Data Index: 577171 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1062. Min Act: -0.0001

Data Index: 1039653 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.0901. Min Act: -0.0001

Data Index: 382398 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1068. Min Act: -0.0001

Data Index: 135374 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1087. Min Act: -0.0001

Data Index: 347754 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.0866. Min Act: -0.0001

Data Index: 1335406 (C4 (Web Text))

Max Activating Token Index: 488

Text #16

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.0938. Min Act: -0.0001

Data Index: 1338631 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.0880. Min Act: -0.0001

Data Index: 367981 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.0787. Min Act: -0.0001

Data Index: 925637 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.0749. Min Act: -0.0001

Data Index: 49797 (C4 (Web Text))

Max Activating Token Index: 203