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

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

Neuron 3206 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: 1.7082. Min Range: -1.7082

Max Act: 1.7082. Min Act: -0.0000

Data Index: 524231 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.5890. Min Act: -0.0000

Data Index: 252890 (C4 (Web Text))

Max Activating Token Index: 577

Text #2

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.4062. Min Act: -0.0000

Data Index: 330261 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.5472. Min Act: -0.0000

Data Index: 1011027 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.3355. Min Act: -0.0000

Data Index: 59654 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.3457. Min Act: -0.0000

Data Index: 908476 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.3517. Min Act: -0.0000

Data Index: 592484 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.4567. Min Act: -0.0000

Data Index: 590347 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.2408. Min Act: -0.0000

Data Index: 628657 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.3887. Min Act: -0.0000

Data Index: 561443 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.3114. Min Act: -0.0000

Data Index: 158091 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.2116. Min Act: -0.0000

Data Index: 86075 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.2089. Min Act: -0.0000

Data Index: 108924 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.2684. Min Act: -0.0000

Data Index: 350034 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.2234. Min Act: -0.0000

Data Index: 938348 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.2447. Min Act: -0.0000

Data Index: 998732 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.2382. Min Act: -0.0000

Data Index: 934684 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.3074. Min Act: -0.0000

Data Index: 34270 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.2502. Min Act: -0.0000

Data Index: 1142151 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.2235. Min Act: -0.0000

Data Index: 216194 (C4 (Web Text))

Max Activating Token Index: 362