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

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

Neuron 4487 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: 1.2906. Min Range: -1.2906

Max Act: 1.2906. Min Act: -0.0000

Data Index: 248947 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 1.2906. Min Range: -1.2906

Max Act: 1.2699. Min Act: -0.0000

Data Index: 559915 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 1.2906. Min Range: -1.2906

Max Act: 1.2405. Min Act: -0.0000

Data Index: 897178 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 1.2906. Min Range: -1.2906

Max Act: 1.1705. Min Act: -0.0000

Data Index: 578422 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 1.2906. Min Range: -1.2906

Max Act: 1.1900. Min Act: -0.0000

Data Index: 128382 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 1.2906. Min Range: -1.2906

Max Act: 1.2580. Min Act: -0.0000

Data Index: 1164678 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 1.2906. Min Range: -1.2906

Max Act: 1.1941. Min Act: -0.0000

Data Index: 633637 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 1.2906. Min Range: -1.2906

Max Act: 1.1406. Min Act: -0.0000

Data Index: 1257316 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 1.2906. Min Range: -1.2906

Max Act: 1.1011. Min Act: -0.0000

Data Index: 361789 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 1.2906. Min Range: -1.2906

Max Act: 1.1267. Min Act: -0.0000

Data Index: 776931 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 1.2906. Min Range: -1.2906

Max Act: 1.1182. Min Act: -0.0000

Data Index: 175801 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 1.2906. Min Range: -1.2906

Max Act: 1.1419. Min Act: -0.0000

Data Index: 1009958 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 1.2906. Min Range: -1.2906

Max Act: 1.0956. Min Act: -0.0000

Data Index: 1137776 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 1.2906. Min Range: -1.2906

Max Act: 1.1316. Min Act: -0.0000

Data Index: 1088723 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 1.2906. Min Range: -1.2906

Max Act: 1.1612. Min Act: -0.0000

Data Index: 920898 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 1.2906. Min Range: -1.2906

Max Act: 1.0828. Min Act: -0.0000

Data Index: 48922 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 1.2906. Min Range: -1.2906

Max Act: 1.0736. Min Act: -0.0000

Data Index: 1637611 (Python Code)

Max Activating Token Index: 8

Text #17

Max Range: 1.2906. Min Range: -1.2906

Max Act: 1.0498. Min Act: -0.0000

Data Index: 937429 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 1.2906. Min Range: -1.2906

Max Act: 1.0287. Min Act: -0.0000

Data Index: 84278 (C4 (Web Text))

Max Activating Token Index: 813

Text #19

Max Range: 1.2906. Min Range: -1.2906

Max Act: 1.0554. Min Act: -0.0000

Data Index: 327862 (C4 (Web Text))

Max Activating Token Index: 295