Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2350 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.3343. Min Act: -0.0001

Data Index: 475134 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.1578. Min Act: -0.0002

Data Index: 372144 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.1545. Min Act: -0.0001

Data Index: 1199951 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.0403. Min Act: -0.0002

Data Index: 1172444 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 1.3343. Min Range: -1.3343

Max Act: 0.9894. Min Act: -0.0001

Data Index: 788950 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 1.3343. Min Range: -1.3343

Max Act: 0.9333. Min Act: -0.0001

Data Index: 44789 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.0400. Min Act: -0.0001

Data Index: 1005724 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.0467. Min Act: -0.0001

Data Index: 175452 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.0314. Min Act: -0.0001

Data Index: 626395 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 1.3343. Min Range: -1.3343

Max Act: 0.8719. Min Act: -0.0002

Data Index: 54127 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 1.3343. Min Range: -1.3343

Max Act: 0.8691. Min Act: -0.0001

Data Index: 1187021 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.0386. Min Act: -0.0001

Data Index: 697296 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.0359. Min Act: -0.0002

Data Index: 1340365 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.0002. Min Act: -0.0001

Data Index: 1215973 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.0002. Min Act: -0.0001

Data Index: 74662 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 1.3343. Min Range: -1.3343

Max Act: 0.9163. Min Act: -0.0002

Data Index: 780928 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 1.3343. Min Range: -1.3343

Max Act: 0.9115. Min Act: -0.0001

Data Index: 62208 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.0424. Min Act: -0.0001

Data Index: 219821 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.0413. Min Act: -0.0001

Data Index: 1072708 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 1.3343. Min Range: -1.3343

Max Act: 0.9845. Min Act: -0.0002

Data Index: 31657 (C4 (Web Text))

Max Activating Token Index: 460