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

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

Neuron 4338 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.9612. Min Act: -0.0000

Data Index: 588083 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.9471. Min Act: -0.0000

Data Index: 1313206 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.8586. Min Act: -0.0000

Data Index: 951953 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.9026. Min Act: -0.0000

Data Index: 254430 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.8181. Min Act: -0.0000

Data Index: 1342575 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.8190. Min Act: -0.0000

Data Index: 495461 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.8399. Min Act: -0.0000

Data Index: 1241377 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.8004. Min Act: -0.0000

Data Index: 246457 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.8659. Min Act: -0.0000

Data Index: 519506 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.8069. Min Act: -0.0000

Data Index: 270066 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.7783. Min Act: -0.0000

Data Index: 908351 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.7635. Min Act: -0.0000

Data Index: 327608 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.7577. Min Act: -0.0000

Data Index: 630860 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.7475. Min Act: -0.0000

Data Index: 435209 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.6880. Min Act: -0.0000

Data Index: 1044609 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.7223. Min Act: -0.0000

Data Index: 1067510 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.7160. Min Act: -0.0000

Data Index: 1220705 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.7607. Min Act: -0.0000

Data Index: 767857 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.7579. Min Act: -0.0000

Data Index: 1063472 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.7475. Min Act: -0.0000

Data Index: 921264 (C4 (Web Text))

Max Activating Token Index: 37