Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3481 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0520. Min Act: -0.0000

Data Index: 1100354 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0452. Min Act: -0.0000

Data Index: 2105 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0414. Min Act: -0.0000

Data Index: 877935 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0465. Min Act: -0.0000

Data Index: 1511803 (Python Code)

Max Activating Token Index: 80

Text #4

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0422. Min Act: -0.0000

Data Index: 1534075 (Python Code)

Max Activating Token Index: 940

Text #5

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0418. Min Act: -0.0000

Data Index: 1561397 (Python Code)

Max Activating Token Index: 340

Text #6

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0392. Min Act: -0.0000

Data Index: 1440212 (Python Code)

Max Activating Token Index: 354

Text #7

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0390. Min Act: -0.0000

Data Index: 1469814 (Python Code)

Max Activating Token Index: 352

Text #8

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0360. Min Act: -0.0000

Data Index: 1577361 (Python Code)

Max Activating Token Index: 764

Text #9

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0374. Min Act: -0.0000

Data Index: 1372921 (Python Code)

Max Activating Token Index: 342

Text #10

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0360. Min Act: -0.0000

Data Index: 1445793 (Python Code)

Max Activating Token Index: 691

Text #11

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0349. Min Act: -0.0000

Data Index: 1437053 (Python Code)

Max Activating Token Index: 483

Text #12

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0345. Min Act: -0.0000

Data Index: 1393107 (Python Code)

Max Activating Token Index: 451

Text #13

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0320. Min Act: -0.0000

Data Index: 1533858 (Python Code)

Max Activating Token Index: 721

Text #14

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0331. Min Act: -0.0000

Data Index: 1465109 (Python Code)

Max Activating Token Index: 644

Text #15

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0342. Min Act: -0.0000

Data Index: 1391741 (Python Code)

Max Activating Token Index: 838

Text #16

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0366. Min Act: -0.0000

Data Index: 1223008 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0327. Min Act: -0.0000

Data Index: 1592149 (Python Code)

Max Activating Token Index: 872

Text #18

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0351. Min Act: -0.0000

Data Index: 1605897 (Python Code)

Max Activating Token Index: 492

Text #19

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0314. Min Act: -0.0000

Data Index: 1482319 (Python Code)

Max Activating Token Index: 648