Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3592 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1602. Min Act: -0.0001

Data Index: 667285 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1543. Min Act: -0.0001

Data Index: 977787 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1420. Min Act: -0.0000

Data Index: 620641 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1470. Min Act: -0.0001

Data Index: 1089673 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1481. Min Act: -0.0001

Data Index: 438339 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1318. Min Act: -0.0001

Data Index: 1223630 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1402. Min Act: -0.0001

Data Index: 1270356 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1409. Min Act: -0.0001

Data Index: 150822 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1441. Min Act: -0.0001

Data Index: 309482 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1344. Min Act: -0.0001

Data Index: 328731 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1284. Min Act: -0.0001

Data Index: 266696 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1369. Min Act: -0.0001

Data Index: 851432 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1378. Min Act: -0.0001

Data Index: 625706 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1361. Min Act: -0.0000

Data Index: 488310 (C4 (Web Text))

Max Activating Token Index: 991

Text #14

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1360. Min Act: -0.0001

Data Index: 981682 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1338. Min Act: -0.0001

Data Index: 910135 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1251. Min Act: -0.0001

Data Index: 637083 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1319. Min Act: -0.0000

Data Index: 144695 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1470. Min Act: -0.0001

Data Index: 390970 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1322. Min Act: -0.0001

Data Index: 233087 (C4 (Web Text))

Max Activating Token Index: 949