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

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

Neuron 371 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: 1.6987. Min Range: -1.6987

Max Act: 1.6987. Min Act: -0.0000

Data Index: 822960 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.3163. Min Act: -0.0000

Data Index: 448185 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.2659. Min Act: -0.0000

Data Index: 584431 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.2627. Min Act: -0.0000

Data Index: 913154 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.2177. Min Act: -0.0000

Data Index: 321269 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.1919. Min Act: -0.0000

Data Index: 763389 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.1531. Min Act: -0.0000

Data Index: 858248 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.1006. Min Act: -0.0000

Data Index: 888120 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 1.6987. Min Range: -1.6987

Max Act: 0.9534. Min Act: -0.0000

Data Index: 968807 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 1.6987. Min Range: -1.6987

Max Act: 0.9903. Min Act: -0.0000

Data Index: 483192 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.0189. Min Act: -0.0000

Data Index: 310149 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 1.6987. Min Range: -1.6987

Max Act: 0.9225. Min Act: -0.0000

Data Index: 1134943 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 1.6987. Min Range: -1.6987

Max Act: 0.9854. Min Act: -0.0000

Data Index: 768321 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 1.6987. Min Range: -1.6987

Max Act: 0.9762. Min Act: -0.0000

Data Index: 333119 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 1.6987. Min Range: -1.6987

Max Act: 0.9256. Min Act: -0.0000

Data Index: 38270 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 1.6987. Min Range: -1.6987

Max Act: 0.9765. Min Act: -0.0000

Data Index: 9439 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 1.6987. Min Range: -1.6987

Max Act: 0.9941. Min Act: -0.0000

Data Index: 532388 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 1.6987. Min Range: -1.6987

Max Act: 0.9401. Min Act: -0.0000

Data Index: 1269523 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 1.6987. Min Range: -1.6987

Max Act: 0.9919. Min Act: -0.0000

Data Index: 637011 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 1.6987. Min Range: -1.6987

Max Act: 0.9424. Min Act: -0.0000

Data Index: 68937 (C4 (Web Text))

Max Activating Token Index: 269