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

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

Neuron 4523 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1173. Min Range: -5.1173

Max Act: 5.1173. Min Act: -0.0000

Data Index: 552141 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 5.1173. Min Range: -5.1173

Max Act: 4.6084. Min Act: -0.0000

Data Index: 212255 (C4 (Web Text))

Max Activating Token Index: 420

Text #2

Max Range: 5.1173. Min Range: -5.1173

Max Act: 4.5622. Min Act: -0.0000

Data Index: 8722 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 5.1173. Min Range: -5.1173

Max Act: 4.5933. Min Act: -0.0000

Data Index: 937817 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 5.1173. Min Range: -5.1173

Max Act: 4.3032. Min Act: -0.0000

Data Index: 922468 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 5.1173. Min Range: -5.1173

Max Act: 4.1200. Min Act: -0.0000

Data Index: 233762 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 5.1173. Min Range: -5.1173

Max Act: 3.6690. Min Act: -0.0000

Data Index: 1147674 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 5.1173. Min Range: -5.1173

Max Act: 3.6589. Min Act: -0.0000

Data Index: 1033249 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 5.1173. Min Range: -5.1173

Max Act: 3.6269. Min Act: -0.0000

Data Index: 279755 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 5.1173. Min Range: -5.1173

Max Act: 3.6136. Min Act: -0.0000

Data Index: 380167 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 5.1173. Min Range: -5.1173

Max Act: 3.2941. Min Act: -0.0000

Data Index: 795888 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 5.1173. Min Range: -5.1173

Max Act: 3.1948. Min Act: -0.0000

Data Index: 1121319 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 5.1173. Min Range: -5.1173

Max Act: 3.1630. Min Act: -0.0000

Data Index: 750670 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 5.1173. Min Range: -5.1173

Max Act: 3.1610. Min Act: -0.0000

Data Index: 1353703 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 5.1173. Min Range: -5.1173

Max Act: 2.9264. Min Act: -0.0000

Data Index: 895135 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 5.1173. Min Range: -5.1173

Max Act: 3.0574. Min Act: -0.0000

Data Index: 1097238 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 5.1173. Min Range: -5.1173

Max Act: 2.9052. Min Act: -0.0000

Data Index: 145820 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 5.1173. Min Range: -5.1173

Max Act: 3.0772. Min Act: -0.0000

Data Index: 936181 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 5.1173. Min Range: -5.1173

Max Act: 2.7343. Min Act: -0.0000

Data Index: 1321834 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 5.1173. Min Range: -5.1173

Max Act: 2.7062. Min Act: -0.0000

Data Index: 1284095 (C4 (Web Text))

Max Activating Token Index: 889