Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2634 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7255. Min Range: -0.7255

Max Act: 0.7255. Min Act: -0.0001

Data Index: 1194720 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 0.7255. Min Range: -0.7255

Max Act: 0.5155. Min Act: -0.0001

Data Index: 866550 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.7255. Min Range: -0.7255

Max Act: 0.4864. Min Act: -0.0001

Data Index: 690030 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 0.7255. Min Range: -0.7255

Max Act: 0.4570. Min Act: -0.0001

Data Index: 763477 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 0.7255. Min Range: -0.7255

Max Act: 0.4425. Min Act: -0.0001

Data Index: 1300179 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 0.7255. Min Range: -0.7255

Max Act: 0.3667. Min Act: -0.0001

Data Index: 153588 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 0.7255. Min Range: -0.7255

Max Act: 0.3793. Min Act: -0.0001

Data Index: 1187717 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 0.7255. Min Range: -0.7255

Max Act: 0.3386. Min Act: -0.0001

Data Index: 1255443 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 0.7255. Min Range: -0.7255

Max Act: 0.3489. Min Act: -0.0001

Data Index: 833282 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 0.7255. Min Range: -0.7255

Max Act: 0.3997. Min Act: -0.0001

Data Index: 1142166 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 0.7255. Min Range: -0.7255

Max Act: 0.3770. Min Act: -0.0001

Data Index: 800188 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 0.7255. Min Range: -0.7255

Max Act: 0.3854. Min Act: -0.0001

Data Index: 666044 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 0.7255. Min Range: -0.7255

Max Act: 0.3539. Min Act: -0.0001

Data Index: 417499 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 0.7255. Min Range: -0.7255

Max Act: 0.3409. Min Act: -0.0001

Data Index: 675684 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 0.7255. Min Range: -0.7255

Max Act: 0.3625. Min Act: -0.0001

Data Index: 1160185 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 0.7255. Min Range: -0.7255

Max Act: 0.3271. Min Act: -0.0001

Data Index: 818346 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.7255. Min Range: -0.7255

Max Act: 0.3523. Min Act: -0.0001

Data Index: 345493 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.7255. Min Range: -0.7255

Max Act: 0.3467. Min Act: -0.0001

Data Index: 435618 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 0.7255. Min Range: -0.7255

Max Act: 0.4141. Min Act: -0.0001

Data Index: 176640 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 0.7255. Min Range: -0.7255

Max Act: 0.3199. Min Act: -0.0001

Data Index: 60350 (C4 (Web Text))

Max Activating Token Index: 553