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

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

Neuron 686 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9518. Min Range: -1.9518

Max Act: 1.9518. Min Act: -0.0000

Data Index: 1262694 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 1.9518. Min Range: -1.9518

Max Act: 1.5979. Min Act: -0.0000

Data Index: 65003 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 1.9518. Min Range: -1.9518

Max Act: 1.7805. Min Act: -0.0000

Data Index: 1274542 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 1.9518. Min Range: -1.9518

Max Act: 1.6296. Min Act: -0.0000

Data Index: 535741 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 1.9518. Min Range: -1.9518

Max Act: 1.6006. Min Act: -0.0000

Data Index: 460677 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 1.9518. Min Range: -1.9518

Max Act: 1.5054. Min Act: -0.0000

Data Index: 909279 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 1.9518. Min Range: -1.9518

Max Act: 1.4836. Min Act: -0.0000

Data Index: 537628 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 1.9518. Min Range: -1.9518

Max Act: 1.4728. Min Act: -0.0000

Data Index: 660850 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 1.9518. Min Range: -1.9518

Max Act: 1.4739. Min Act: -0.0000

Data Index: 512158 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 1.9518. Min Range: -1.9518

Max Act: 1.3709. Min Act: -0.0000

Data Index: 789206 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 1.9518. Min Range: -1.9518

Max Act: 1.3312. Min Act: -0.0000

Data Index: 1142372 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 1.9518. Min Range: -1.9518

Max Act: 1.5523. Min Act: -0.0000

Data Index: 369723 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 1.9518. Min Range: -1.9518

Max Act: 1.3990. Min Act: -0.0000

Data Index: 601813 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 1.9518. Min Range: -1.9518

Max Act: 1.3768. Min Act: -0.0000

Data Index: 200191 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 1.9518. Min Range: -1.9518

Max Act: 1.3086. Min Act: -0.0000

Data Index: 752545 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 1.9518. Min Range: -1.9518

Max Act: 1.3777. Min Act: -0.0000

Data Index: 218284 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 1.9518. Min Range: -1.9518

Max Act: 1.2914. Min Act: -0.0000

Data Index: 1059113 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 1.9518. Min Range: -1.9518

Max Act: 1.2680. Min Act: -0.0000

Data Index: 752015 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 1.9518. Min Range: -1.9518

Max Act: 1.4194. Min Act: -0.0000

Data Index: 1088579 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 1.9518. Min Range: -1.9518

Max Act: 1.3168. Min Act: -0.0000

Data Index: 823905 (C4 (Web Text))

Max Activating Token Index: 386