Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1409 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.3665. Min Act: -0.0001

Data Index: 680315 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2972. Min Act: -0.0001

Data Index: 1243520 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2809. Min Act: -0.0001

Data Index: 195473 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2725. Min Act: -0.0001

Data Index: 865061 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2656. Min Act: -0.0001

Data Index: 795881 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2634. Min Act: -0.0001

Data Index: 620661 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2750. Min Act: -0.0001

Data Index: 537623 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2528. Min Act: -0.0001

Data Index: 873067 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2406. Min Act: -0.0001

Data Index: 654516 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2379. Min Act: -0.0001

Data Index: 72863 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2667. Min Act: -0.0001

Data Index: 758102 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2391. Min Act: -0.0001

Data Index: 355727 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2320. Min Act: -0.0001

Data Index: 440411 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2126. Min Act: -0.0001

Data Index: 96524 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2286. Min Act: -0.0001

Data Index: 1076008 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2277. Min Act: -0.0001

Data Index: 931853 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2137. Min Act: -0.0001

Data Index: 197564 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2168. Min Act: -0.0001

Data Index: 319716 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2129. Min Act: -0.0001

Data Index: 451664 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2260. Min Act: -0.0001

Data Index: 158863 (C4 (Web Text))

Max Activating Token Index: 160