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

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

Neuron 3312 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: 0.6505. Min Range: -0.6505

Max Act: 0.6505. Min Act: -0.0000

Data Index: 656643 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 0.6505. Min Range: -0.6505

Max Act: 0.6129. Min Act: -0.0000

Data Index: 675438 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 0.6505. Min Range: -0.6505

Max Act: 0.6294. Min Act: -0.0000

Data Index: 931384 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 0.6505. Min Range: -0.6505

Max Act: 0.5558. Min Act: 0.0000

Data Index: 959381 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.6505. Min Range: -0.6505

Max Act: 0.5271. Min Act: -0.0000

Data Index: 725709 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.6505. Min Range: -0.6505

Max Act: 0.4835. Min Act: -0.0000

Data Index: 22244 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 0.6505. Min Range: -0.6505

Max Act: 0.4859. Min Act: -0.0000

Data Index: 479721 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 0.6505. Min Range: -0.6505

Max Act: 0.4807. Min Act: 0.0001

Data Index: 582480 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.6505. Min Range: -0.6505

Max Act: 0.4614. Min Act: 0.0000

Data Index: 689339 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 0.6505. Min Range: -0.6505

Max Act: 0.4776. Min Act: -0.0000

Data Index: 617016 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 0.6505. Min Range: -0.6505

Max Act: 0.4629. Min Act: -0.0000

Data Index: 39288 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 0.6505. Min Range: -0.6505

Max Act: 0.4471. Min Act: -0.0000

Data Index: 962865 (C4 (Web Text))

Max Activating Token Index: 960

Text #12

Max Range: 0.6505. Min Range: -0.6505

Max Act: 0.4624. Min Act: -0.0000

Data Index: 913176 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 0.6505. Min Range: -0.6505

Max Act: 0.4834. Min Act: -0.0000

Data Index: 221756 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.6505. Min Range: -0.6505

Max Act: 0.4467. Min Act: -0.0001

Data Index: 385548 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 0.6505. Min Range: -0.6505

Max Act: 0.4478. Min Act: -0.0000

Data Index: 37687 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 0.6505. Min Range: -0.6505

Max Act: 0.4299. Min Act: -0.0000

Data Index: 929705 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 0.6505. Min Range: -0.6505

Max Act: 0.4306. Min Act: -0.0000

Data Index: 1287487 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 0.6505. Min Range: -0.6505

Max Act: 0.4410. Min Act: -0.0000

Data Index: 831871 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 0.6505. Min Range: -0.6505

Max Act: 0.4193. Min Act: -0.0000

Data Index: 767461 (C4 (Web Text))

Max Activating Token Index: 227