Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3988 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2377. Min Range: -2.2377

Max Act: 2.2377. Min Act: -0.0000

Data Index: 978514 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 2.2377. Min Range: -2.2377

Max Act: 1.7297. Min Act: -0.0000

Data Index: 248967 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 2.2377. Min Range: -2.2377

Max Act: 1.7121. Min Act: -0.0000

Data Index: 1205689 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 2.2377. Min Range: -2.2377

Max Act: 1.4867. Min Act: -0.0000

Data Index: 664191 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 2.2377. Min Range: -2.2377

Max Act: 1.4784. Min Act: -0.0000

Data Index: 1000815 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 2.2377. Min Range: -2.2377

Max Act: 1.2634. Min Act: -0.0000

Data Index: 66164 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 2.2377. Min Range: -2.2377

Max Act: 1.3430. Min Act: -0.0000

Data Index: 405788 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 2.2377. Min Range: -2.2377

Max Act: 1.3059. Min Act: -0.0000

Data Index: 38351 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 2.2377. Min Range: -2.2377

Max Act: 1.2184. Min Act: -0.0000

Data Index: 384150 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 2.2377. Min Range: -2.2377

Max Act: 1.1541. Min Act: -0.0000

Data Index: 1029583 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 2.2377. Min Range: -2.2377

Max Act: 1.0528. Min Act: -0.0000

Data Index: 589436 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 2.2377. Min Range: -2.2377

Max Act: 0.9936. Min Act: -0.0000

Data Index: 320562 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 2.2377. Min Range: -2.2377

Max Act: 0.9811. Min Act: -0.0000

Data Index: 889212 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 2.2377. Min Range: -2.2377

Max Act: 0.9860. Min Act: -0.0000

Data Index: 1102859 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 2.2377. Min Range: -2.2377

Max Act: 0.9606. Min Act: -0.0000

Data Index: 422553 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 2.2377. Min Range: -2.2377

Max Act: 0.9467. Min Act: -0.0000

Data Index: 1154597 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 2.2377. Min Range: -2.2377

Max Act: 0.9022. Min Act: -0.0000

Data Index: 184703 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 2.2377. Min Range: -2.2377

Max Act: 0.9519. Min Act: -0.0000

Data Index: 797859 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 2.2377. Min Range: -2.2377

Max Act: 0.9039. Min Act: -0.0000

Data Index: 954529 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 2.2377. Min Range: -2.2377

Max Act: 0.8982. Min Act: -0.0000

Data Index: 81648 (C4 (Web Text))

Max Activating Token Index: 153