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

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

Neuron 4117 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1393. Min Range: -1.1393

Max Act: 1.1393. Min Act: -0.0000

Data Index: 493866 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 1.1393. Min Range: -1.1393

Max Act: 1.1033. Min Act: -0.0000

Data Index: 1284816 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 1.1393. Min Range: -1.1393

Max Act: 1.0787. Min Act: -0.0000

Data Index: 864040 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.9805. Min Act: -0.0000

Data Index: 796841 (C4 (Web Text))

Max Activating Token Index: 572

Text #4

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.9609. Min Act: -0.0000

Data Index: 218360 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.9367. Min Act: -0.0000

Data Index: 828056 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.9086. Min Act: -0.0000

Data Index: 1197248 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.9154. Min Act: -0.0000

Data Index: 720218 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.8317. Min Act: -0.0000

Data Index: 570431 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.8850. Min Act: -0.0000

Data Index: 54720 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.8473. Min Act: -0.0000

Data Index: 401219 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.8197. Min Act: -0.0000

Data Index: 1225058 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.7951. Min Act: -0.0000

Data Index: 540900 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.8256. Min Act: -0.0000

Data Index: 262988 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.7657. Min Act: -0.0000

Data Index: 718930 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.7676. Min Act: -0.0000

Data Index: 527034 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.7351. Min Act: -0.0000

Data Index: 680264 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.7465. Min Act: -0.0000

Data Index: 705736 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.7895. Min Act: -0.0000

Data Index: 2734 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.8149. Min Act: -0.0000

Data Index: 2588 (C4 (Web Text))

Max Activating Token Index: 184