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

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

Neuron 3641 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.8423. Min Act: -0.0000

Data Index: 468407 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6145. Min Act: -0.0000

Data Index: 721072 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5728. Min Act: -0.0000

Data Index: 914982 (C4 (Web Text))

Max Activating Token Index: 488

Text #3

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5555. Min Act: -0.0000

Data Index: 1037349 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5408. Min Act: 0.0000

Data Index: 870360 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5383. Min Act: -0.0000

Data Index: 549707 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.4817. Min Act: -0.0000

Data Index: 92070 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5175. Min Act: -0.0000

Data Index: 1227241 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.4502. Min Act: -0.0000

Data Index: 676524 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.4265. Min Act: -0.0000

Data Index: 464642 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.4645. Min Act: -0.0000

Data Index: 1317582 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.4436. Min Act: -0.0000

Data Index: 1358551 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.4294. Min Act: -0.0000

Data Index: 344395 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.4386. Min Act: -0.0000

Data Index: 1205457 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.4066. Min Act: -0.0000

Data Index: 1242576 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.3727. Min Act: -0.0000

Data Index: 157907 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.3925. Min Act: -0.0000

Data Index: 953540 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.3834. Min Act: -0.0000

Data Index: 1159899 (C4 (Web Text))

Max Activating Token Index: 70

Text #18

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.3775. Min Act: -0.0000

Data Index: 309955 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.3628. Min Act: -0.0000

Data Index: 417070 (C4 (Web Text))

Max Activating Token Index: 555