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

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

Neuron 188 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.6141. Min Act: -0.0000

Data Index: 178662 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5977. Min Act: -0.0000

Data Index: 712922 (C4 (Web Text))

Max Activating Token Index: 758

Text #2

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.6241. Min Act: -0.0000

Data Index: 1162012 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.6135. Min Act: -0.0000

Data Index: 195185 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5850. Min Act: -0.0000

Data Index: 684610 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5524. Min Act: -0.0000

Data Index: 841182 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5430. Min Act: -0.0000

Data Index: 1235265 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5559. Min Act: -0.0000

Data Index: 463155 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5545. Min Act: -0.0000

Data Index: 434732 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5279. Min Act: -0.0000

Data Index: 744885 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5456. Min Act: -0.0000

Data Index: 607059 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5800. Min Act: -0.0000

Data Index: 349861 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5588. Min Act: -0.0000

Data Index: 393636 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5066. Min Act: -0.0000

Data Index: 579293 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5054. Min Act: -0.0000

Data Index: 538877 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5355. Min Act: -0.0000

Data Index: 1193879 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5150. Min Act: -0.0000

Data Index: 502172 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5304. Min Act: -0.0000

Data Index: 973834 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4906. Min Act: -0.0000

Data Index: 960866 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4929. Min Act: -0.0000

Data Index: 1141523 (C4 (Web Text))

Max Activating Token Index: 730