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

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

Neuron 1834 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4717. Min Range: -2.4717

Max Act: 2.4717. Min Act: -0.0000

Data Index: 1526655 (Python Code)

Max Activating Token Index: 427

Text #1

Max Range: 2.4717. Min Range: -2.4717

Max Act: 2.4541. Min Act: -0.0000

Data Index: 1399329 (Python Code)

Max Activating Token Index: 616

Text #2

Max Range: 2.4717. Min Range: -2.4717

Max Act: 2.4175. Min Act: -0.0000

Data Index: 1445437 (Python Code)

Max Activating Token Index: 575

Text #3

Max Range: 2.4717. Min Range: -2.4717

Max Act: 2.2851. Min Act: -0.0000

Data Index: 1652437 (Python Code)

Max Activating Token Index: 398

Text #4

Max Range: 2.4717. Min Range: -2.4717

Max Act: 2.4185. Min Act: -0.0000

Data Index: 1623777 (Python Code)

Max Activating Token Index: 39

Text #5

Max Range: 2.4717. Min Range: -2.4717

Max Act: 2.1433. Min Act: -0.0000

Data Index: 1520526 (Python Code)

Max Activating Token Index: 674

Text #6

Max Range: 2.4717. Min Range: -2.4717

Max Act: 2.3258. Min Act: -0.0000

Data Index: 1392993 (Python Code)

Max Activating Token Index: 614

Text #7

Max Range: 2.4717. Min Range: -2.4717

Max Act: 2.2077. Min Act: -0.0000

Data Index: 1366603 (Python Code)

Max Activating Token Index: 227

Text #8

Max Range: 2.4717. Min Range: -2.4717

Max Act: 2.1979. Min Act: -0.0000

Data Index: 1526351 (Python Code)

Max Activating Token Index: 1002

Text #9

Max Range: 2.4717. Min Range: -2.4717

Max Act: 2.1856. Min Act: -0.0000

Data Index: 1554268 (Python Code)

Max Activating Token Index: 59

Text #10

Max Range: 2.4717. Min Range: -2.4717

Max Act: 2.1854. Min Act: -0.0001

Data Index: 1544530 (Python Code)

Max Activating Token Index: 56

Text #11

Max Range: 2.4717. Min Range: -2.4717

Max Act: 2.0285. Min Act: -0.0000

Data Index: 1525383 (Python Code)

Max Activating Token Index: 647

Text #12

Max Range: 2.4717. Min Range: -2.4717

Max Act: 2.1296. Min Act: -0.0000

Data Index: 1618083 (Python Code)

Max Activating Token Index: 576

Text #13

Max Range: 2.4717. Min Range: -2.4717

Max Act: 2.1294. Min Act: -0.0000

Data Index: 1542048 (Python Code)

Max Activating Token Index: 247

Text #14

Max Range: 2.4717. Min Range: -2.4717

Max Act: 2.1308. Min Act: -0.0000

Data Index: 1484405 (Python Code)

Max Activating Token Index: 501

Text #15

Max Range: 2.4717. Min Range: -2.4717

Max Act: 2.1324. Min Act: -0.0000

Data Index: 1458666 (Python Code)

Max Activating Token Index: 319

Text #16

Max Range: 2.4717. Min Range: -2.4717

Max Act: 2.2228. Min Act: -0.0000

Data Index: 1518550 (Python Code)

Max Activating Token Index: 72

Text #17

Max Range: 2.4717. Min Range: -2.4717

Max Act: 2.1247. Min Act: -0.0001

Data Index: 1398674 (Python Code)

Max Activating Token Index: 174

Text #18

Max Range: 2.4717. Min Range: -2.4717

Max Act: 1.9401. Min Act: -0.0000

Data Index: 1518659 (Python Code)

Max Activating Token Index: 442

Text #19

Max Range: 2.4717. Min Range: -2.4717

Max Act: 2.0647. Min Act: -0.0000

Data Index: 1493346 (Python Code)

Max Activating Token Index: 271