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

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

Neuron 94 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1774. Min Act: -0.0000

Data Index: 1248127 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1668. Min Act: -0.0000

Data Index: 117904 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1644. Min Act: -0.0000

Data Index: 153808 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1600. Min Act: -0.0000

Data Index: 996215 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1432. Min Act: -0.0000

Data Index: 1151750 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1380. Min Act: -0.0000

Data Index: 1098698 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1333. Min Act: -0.0000

Data Index: 568296 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1360. Min Act: -0.0000

Data Index: 1261497 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1342. Min Act: -0.0000

Data Index: 190570 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1320. Min Act: -0.0000

Data Index: 64674 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1311. Min Act: -0.0000

Data Index: 853102 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1262. Min Act: -0.0000

Data Index: 1369160 (Python Code)

Max Activating Token Index: 463

Text #12

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1259. Min Act: -0.0000

Data Index: 1088407 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1306. Min Act: -0.0000

Data Index: 265114 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1161. Min Act: -0.0000

Data Index: 1407153 (Python Code)

Max Activating Token Index: 225

Text #15

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1278. Min Act: -0.0000

Data Index: 828466 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1259. Min Act: -0.0000

Data Index: 394155 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1221. Min Act: -0.0000

Data Index: 411095 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1216. Min Act: -0.0000

Data Index: 1031104 (C4 (Web Text))

Max Activating Token Index: 548

Text #19

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1141. Min Act: -0.0000

Data Index: 287726 (C4 (Web Text))

Max Activating Token Index: 428