Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1474 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2592. Min Act: -0.0001

Data Index: 836654 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2414. Min Act: -0.0001

Data Index: 180994 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2325. Min Act: -0.0001

Data Index: 95804 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2386. Min Act: -0.0001

Data Index: 1122471 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2304. Min Act: -0.0001

Data Index: 1301067 (C4 (Web Text))

Max Activating Token Index: 412

Text #5

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2001. Min Act: -0.0001

Data Index: 233072 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2205. Min Act: -0.0001

Data Index: 658674 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1969. Min Act: -0.0001

Data Index: 498277 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2110. Min Act: -0.0001

Data Index: 353250 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1996. Min Act: -0.0001

Data Index: 285622 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1709. Min Act: -0.0001

Data Index: 1113740 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1858. Min Act: -0.0001

Data Index: 136917 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1995. Min Act: -0.0001

Data Index: 724422 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1824. Min Act: -0.0001

Data Index: 1047801 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1888. Min Act: -0.0001

Data Index: 127818 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1779. Min Act: -0.0001

Data Index: 934947 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1890. Min Act: -0.0001

Data Index: 1035360 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1834. Min Act: -0.0001

Data Index: 1199991 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1751. Min Act: -0.0001

Data Index: 1298379 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1657. Min Act: -0.0001

Data Index: 974944 (C4 (Web Text))

Max Activating Token Index: 418