Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1859 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0694. Min Act: -0.0003

Data Index: 381226 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0639. Min Act: -0.0003

Data Index: 810503 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0599. Min Act: -0.0003

Data Index: 1061639 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0607. Min Act: -0.0003

Data Index: 134355 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0585. Min Act: -0.0003

Data Index: 318315 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0595. Min Act: -0.0003

Data Index: 199394 (C4 (Web Text))

Max Activating Token Index: 384

Text #6

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0584. Min Act: -0.0003

Data Index: 1025553 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0613. Min Act: -0.0003

Data Index: 810895 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0583. Min Act: -0.0003

Data Index: 1172768 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0578. Min Act: -0.0003

Data Index: 851248 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0583. Min Act: -0.0003

Data Index: 1297224 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0568. Min Act: -0.0003

Data Index: 235105 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0591. Min Act: -0.0003

Data Index: 451653 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0567. Min Act: -0.0003

Data Index: 275331 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0569. Min Act: -0.0003

Data Index: 616629 (C4 (Web Text))

Max Activating Token Index: 835

Text #15

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0566. Min Act: -0.0003

Data Index: 439053 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0585. Min Act: -0.0003

Data Index: 1219510 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0593. Min Act: -0.0003

Data Index: 1334929 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0584. Min Act: -0.0003

Data Index: 1329395 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0595. Min Act: -0.0003

Data Index: 1075065 (C4 (Web Text))

Max Activating Token Index: 962