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

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

Neuron 4918 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.4845. Min Act: -0.0000

Data Index: 1598818 (Python Code)

Max Activating Token Index: 352

Text #1

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.3327. Min Act: -0.0000

Data Index: 1521727 (Python Code)

Max Activating Token Index: 851

Text #2

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.3945. Min Act: -0.0000

Data Index: 1156990 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.3331. Min Act: -0.0000

Data Index: 1628595 (Python Code)

Max Activating Token Index: 467

Text #4

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.2950. Min Act: -0.0000

Data Index: 1533812 (Python Code)

Max Activating Token Index: 346

Text #5

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.3270. Min Act: -0.0000

Data Index: 1424271 (Python Code)

Max Activating Token Index: 492

Text #6

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.2882. Min Act: -0.0000

Data Index: 1653114 (Python Code)

Max Activating Token Index: 182

Text #7

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.2647. Min Act: -0.0000

Data Index: 1400610 (Python Code)

Max Activating Token Index: 465

Text #8

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.2535. Min Act: -0.0000

Data Index: 1384839 (Python Code)

Max Activating Token Index: 315

Text #9

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.1807. Min Act: -0.0000

Data Index: 1627479 (Python Code)

Max Activating Token Index: 660

Text #10

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.1541. Min Act: -0.0000

Data Index: 1388010 (Python Code)

Max Activating Token Index: 779

Text #11

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.2082. Min Act: -0.0000

Data Index: 1537176 (Python Code)

Max Activating Token Index: 234

Text #12

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.1853. Min Act: -0.0000

Data Index: 1436532 (Python Code)

Max Activating Token Index: 374

Text #13

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.1620. Min Act: -0.0000

Data Index: 1435676 (Python Code)

Max Activating Token Index: 320

Text #14

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.1854. Min Act: -0.0000

Data Index: 1557092 (Python Code)

Max Activating Token Index: 425

Text #15

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.0952. Min Act: -0.0000

Data Index: 1367658 (Python Code)

Max Activating Token Index: 376

Text #16

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.1257. Min Act: -0.0000

Data Index: 1644283 (Python Code)

Max Activating Token Index: 279

Text #17

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.1163. Min Act: -0.0000

Data Index: 1562863 (Python Code)

Max Activating Token Index: 119

Text #18

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.1567. Min Act: -0.0000

Data Index: 1381220 (Python Code)

Max Activating Token Index: 311

Text #19

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.1395. Min Act: -0.0000

Data Index: 1643997 (Python Code)

Max Activating Token Index: 336