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

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

Neuron 3049 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.3671. Min Act: -0.0001

Data Index: 927017 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.3013. Min Act: -0.0001

Data Index: 1115531 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2935. Min Act: -0.0001

Data Index: 130679 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2680. Min Act: -0.0001

Data Index: 706860 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2495. Min Act: -0.0001

Data Index: 1337179 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2479. Min Act: -0.0001

Data Index: 1173175 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2532. Min Act: -0.0001

Data Index: 769427 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2530. Min Act: -0.0001

Data Index: 1062327 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2598. Min Act: -0.0001

Data Index: 963267 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2500. Min Act: -0.0001

Data Index: 1355411 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2568. Min Act: -0.0001

Data Index: 564653 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2440. Min Act: -0.0001

Data Index: 1287986 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2434. Min Act: -0.0001

Data Index: 1140328 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2220. Min Act: -0.0001

Data Index: 895713 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2287. Min Act: -0.0001

Data Index: 129779 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2525. Min Act: -0.0001

Data Index: 6253 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2283. Min Act: -0.0001

Data Index: 180061 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2430. Min Act: -0.0001

Data Index: 397893 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2355. Min Act: -0.0001

Data Index: 1055026 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2242. Min Act: -0.0001

Data Index: 960626 (C4 (Web Text))

Max Activating Token Index: 367