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

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

Neuron 3111 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.6931. Min Act: -0.0000

Data Index: 588843 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.6499. Min Act: -0.0000

Data Index: 1462074 (Python Code)

Max Activating Token Index: 700

Text #2

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.5918. Min Act: -0.0001

Data Index: 1412299 (Python Code)

Max Activating Token Index: 524

Text #3

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.5006. Min Act: -0.0000

Data Index: 1596798 (Python Code)

Max Activating Token Index: 171

Text #4

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.4397. Min Act: -0.0001

Data Index: 283832 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.4655. Min Act: -0.0000

Data Index: 1485233 (Python Code)

Max Activating Token Index: 127

Text #6

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.3229. Min Act: -0.0000

Data Index: 53795 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.4431. Min Act: -0.0000

Data Index: 1459170 (Python Code)

Max Activating Token Index: 58

Text #8

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.3167. Min Act: -0.0000

Data Index: 400408 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.2558. Min Act: -0.0001

Data Index: 1340527 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.2486. Min Act: -0.0001

Data Index: 1635071 (Python Code)

Max Activating Token Index: 723

Text #11

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.2920. Min Act: -0.0000

Data Index: 1442989 (Python Code)

Max Activating Token Index: 87

Text #12

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.2432. Min Act: -0.0000

Data Index: 1413457 (Python Code)

Max Activating Token Index: 15

Text #13

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.2755. Min Act: -0.0001

Data Index: 103154 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.2766. Min Act: -0.0001

Data Index: 816717 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.2361. Min Act: -0.0001

Data Index: 1595295 (Python Code)

Max Activating Token Index: 382

Text #16

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.2241. Min Act: -0.0001

Data Index: 1537330 (Python Code)

Max Activating Token Index: 729

Text #17

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.2687. Min Act: -0.0000

Data Index: 1636908 (Python Code)

Max Activating Token Index: 982

Text #18

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.2960. Min Act: -0.0001

Data Index: 339526 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.1678. Min Act: -0.0000

Data Index: 1566598 (Python Code)

Max Activating Token Index: 561