Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 534 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.3136. Min Act: -0.0001

Data Index: 482364 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.2494. Min Act: -0.0001

Data Index: 278947 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.1683. Min Act: -0.0001

Data Index: 1140928 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.1559. Min Act: -0.0001

Data Index: 1138307 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.1486. Min Act: -0.0001

Data Index: 711359 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.1453. Min Act: -0.0001

Data Index: 591447 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.1472. Min Act: -0.0001

Data Index: 1014256 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.1447. Min Act: -0.0001

Data Index: 162081 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.1444. Min Act: -0.0001

Data Index: 876504 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.1459. Min Act: -0.0001

Data Index: 1280572 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.1373. Min Act: -0.0001

Data Index: 445224 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.1317. Min Act: -0.0001

Data Index: 862420 (C4 (Web Text))

Max Activating Token Index: 259

Text #12

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.1227. Min Act: -0.0001

Data Index: 418929 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.1216. Min Act: -0.0001

Data Index: 1020393 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.1289. Min Act: -0.0001

Data Index: 800856 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.1223. Min Act: -0.0001

Data Index: 661633 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.1215. Min Act: -0.0001

Data Index: 486371 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.1296. Min Act: -0.0001

Data Index: 1080507 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.1206. Min Act: -0.0001

Data Index: 808749 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.1223. Min Act: -0.0001

Data Index: 397314 (C4 (Web Text))

Max Activating Token Index: 107