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

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

Neuron 1585 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.4121. Min Act: -0.0000

Data Index: 1070519 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.3705. Min Act: -0.0000

Data Index: 198895 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.3568. Min Act: -0.0000

Data Index: 1083961 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.3489. Min Act: -0.0000

Data Index: 352786 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.3477. Min Act: -0.0000

Data Index: 53883 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.3484. Min Act: 0.0001

Data Index: 396130 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.3226. Min Act: -0.0000

Data Index: 180406 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.3316. Min Act: 0.0000

Data Index: 236180 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.3217. Min Act: -0.0000

Data Index: 1130443 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.3247. Min Act: 0.0000

Data Index: 180521 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.3002. Min Act: -0.0000

Data Index: 267526 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.2804. Min Act: -0.0000

Data Index: 779528 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.2936. Min Act: -0.0000

Data Index: 890083 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.2866. Min Act: -0.0000

Data Index: 1049094 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.2583. Min Act: -0.0000

Data Index: 622549 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.2998. Min Act: -0.0000

Data Index: 229457 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.2996. Min Act: -0.0000

Data Index: 390619 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.2871. Min Act: 0.0001

Data Index: 242605 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.2777. Min Act: 0.0000

Data Index: 206725 (C4 (Web Text))

Max Activating Token Index: 830

Text #19

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.2881. Min Act: -0.0000

Data Index: 1293207 (C4 (Web Text))

Max Activating Token Index: 199