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

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

Neuron 2003 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2880. Min Range: -2.2880

Max Act: 2.2880. Min Act: -0.0000

Data Index: 60269 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 2.2880. Min Range: -2.2880

Max Act: 1.9851. Min Act: -0.0000

Data Index: 285226 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 2.2880. Min Range: -2.2880

Max Act: 1.8244. Min Act: -0.0000

Data Index: 139082 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 2.2880. Min Range: -2.2880

Max Act: 1.4051. Min Act: -0.0000

Data Index: 1107607 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 2.2880. Min Range: -2.2880

Max Act: 1.3193. Min Act: -0.0000

Data Index: 990232 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 2.2880. Min Range: -2.2880

Max Act: 1.3577. Min Act: -0.0000

Data Index: 239591 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 2.2880. Min Range: -2.2880

Max Act: 1.2205. Min Act: -0.0000

Data Index: 1043087 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 2.2880. Min Range: -2.2880

Max Act: 1.0454. Min Act: -0.0000

Data Index: 584781 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 2.2880. Min Range: -2.2880

Max Act: 1.0927. Min Act: -0.0000

Data Index: 1229608 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 2.2880. Min Range: -2.2880

Max Act: 1.1547. Min Act: -0.0000

Data Index: 484321 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 2.2880. Min Range: -2.2880

Max Act: 1.1235. Min Act: -0.0000

Data Index: 95636 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 2.2880. Min Range: -2.2880

Max Act: 0.9252. Min Act: -0.0000

Data Index: 464006 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 2.2880. Min Range: -2.2880

Max Act: 0.9541. Min Act: -0.0000

Data Index: 1121434 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 2.2880. Min Range: -2.2880

Max Act: 0.9475. Min Act: -0.0000

Data Index: 227904 (C4 (Web Text))

Max Activating Token Index: 972

Text #14

Max Range: 2.2880. Min Range: -2.2880

Max Act: 0.9916. Min Act: -0.0000

Data Index: 246563 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 2.2880. Min Range: -2.2880

Max Act: 0.9817. Min Act: -0.0000

Data Index: 397364 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 2.2880. Min Range: -2.2880

Max Act: 0.9162. Min Act: -0.0000

Data Index: 225380 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 2.2880. Min Range: -2.2880

Max Act: 0.9971. Min Act: -0.0000

Data Index: 277998 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 2.2880. Min Range: -2.2880

Max Act: 0.9317. Min Act: -0.0000

Data Index: 1028877 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 2.2880. Min Range: -2.2880

Max Act: 0.9379. Min Act: -0.0000

Data Index: 842834 (C4 (Web Text))

Max Activating Token Index: 712