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

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

Neuron 3442 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0875. Min Range: -1.0875

Max Act: 1.0875. Min Act: -0.0001

Data Index: 1195184 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.9085. Min Act: -0.0001

Data Index: 592055 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.9162. Min Act: -0.0001

Data Index: 1175187 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.9069. Min Act: -0.0001

Data Index: 809370 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.8500. Min Act: -0.0001

Data Index: 257329 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.9046. Min Act: -0.0001

Data Index: 1293220 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.8808. Min Act: -0.0001

Data Index: 574541 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.8628. Min Act: -0.0001

Data Index: 542184 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.8020. Min Act: -0.0001

Data Index: 833949 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.7857. Min Act: -0.0001

Data Index: 1284241 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.7761. Min Act: -0.0001

Data Index: 1048185 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.7934. Min Act: -0.0001

Data Index: 1111796 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.7415. Min Act: -0.0001

Data Index: 272499 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.8454. Min Act: -0.0001

Data Index: 94999 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.8005. Min Act: -0.0001

Data Index: 504711 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.8251. Min Act: -0.0001

Data Index: 1235494 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.7998. Min Act: -0.0001

Data Index: 695025 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.8590. Min Act: -0.0001

Data Index: 521809 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.8166. Min Act: -0.0001

Data Index: 1316068 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.7503. Min Act: -0.0001

Data Index: 425328 (C4 (Web Text))

Max Activating Token Index: 313