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

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

Neuron 2105 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2674. Min Act: -0.0000

Data Index: 765913 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2624. Min Act: -0.0000

Data Index: 1258333 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2532. Min Act: -0.0001

Data Index: 1220554 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2455. Min Act: -0.0000

Data Index: 1339542 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2530. Min Act: -0.0000

Data Index: 110453 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2658. Min Act: -0.0000

Data Index: 1085321 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2425. Min Act: -0.0000

Data Index: 1185191 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2419. Min Act: -0.0000

Data Index: 1311992 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2362. Min Act: -0.0000

Data Index: 950942 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2322. Min Act: -0.0000

Data Index: 1052577 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2287. Min Act: -0.0000

Data Index: 920381 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2410. Min Act: -0.0001

Data Index: 357472 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2308. Min Act: -0.0001

Data Index: 948649 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2542. Min Act: -0.0001

Data Index: 975228 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2381. Min Act: -0.0000

Data Index: 980845 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2179. Min Act: -0.0000

Data Index: 105561 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2223. Min Act: -0.0000

Data Index: 485509 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2269. Min Act: -0.0000

Data Index: 905884 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2059. Min Act: -0.0000

Data Index: 1096848 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2037. Min Act: -0.0000

Data Index: 710046 (C4 (Web Text))

Max Activating Token Index: 799