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

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

Neuron 1648 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.3058. Min Act: -0.0001

Data Index: 569951 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.3003. Min Act: -0.0001

Data Index: 334537 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2618. Min Act: -0.0001

Data Index: 807287 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2732. Min Act: -0.0001

Data Index: 910981 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2599. Min Act: -0.0000

Data Index: 527124 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2290. Min Act: -0.0000

Data Index: 603743 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1783. Min Act: -0.0000

Data Index: 1144545 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1724. Min Act: -0.0000

Data Index: 1328315 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1871. Min Act: -0.0001

Data Index: 102821 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1494. Min Act: -0.0000

Data Index: 31073 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1478. Min Act: -0.0000

Data Index: 979169 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1455. Min Act: -0.0000

Data Index: 811748 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1339. Min Act: -0.0001

Data Index: 1032379 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1206. Min Act: -0.0001

Data Index: 288117 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1264. Min Act: -0.0000

Data Index: 17461 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1397. Min Act: -0.0000

Data Index: 212698 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1596. Min Act: -0.0001

Data Index: 1207481 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1270. Min Act: -0.0000

Data Index: 245306 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1237. Min Act: -0.0001

Data Index: 977887 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1268. Min Act: -0.0000

Data Index: 922596 (C4 (Web Text))

Max Activating Token Index: 952