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

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

Neuron 707 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6776. Min Act: -0.0001

Data Index: 242447 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6925. Min Act: -0.0001

Data Index: 625513 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6663. Min Act: -0.0001

Data Index: 925234 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6864. Min Act: -0.0001

Data Index: 199065 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6852. Min Act: -0.0001

Data Index: 723078 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6610. Min Act: -0.0001

Data Index: 242239 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6360. Min Act: -0.0001

Data Index: 1160214 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6715. Min Act: -0.0001

Data Index: 557587 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.5919. Min Act: -0.0001

Data Index: 765415 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6691. Min Act: -0.0001

Data Index: 1042340 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6592. Min Act: -0.0001

Data Index: 665743 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6474. Min Act: -0.0001

Data Index: 120500 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6276. Min Act: -0.0001

Data Index: 185537 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.5894. Min Act: -0.0001

Data Index: 160177 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6351. Min Act: -0.0001

Data Index: 1063630 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6151. Min Act: -0.0001

Data Index: 754923 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6285. Min Act: -0.0001

Data Index: 1288134 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.5684. Min Act: -0.0001

Data Index: 587859 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.5714. Min Act: -0.0001

Data Index: 1329603 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6227. Min Act: -0.0001

Data Index: 1248846 (C4 (Web Text))

Max Activating Token Index: 193