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

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

Neuron 428 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.4351. Min Act: -0.0000

Data Index: 1646488 (Python Code)

Max Activating Token Index: 180

Text #1

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.4284. Min Act: -0.0000

Data Index: 1636158 (Python Code)

Max Activating Token Index: 503

Text #2

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.4342. Min Act: -0.0001

Data Index: 1398516 (Python Code)

Max Activating Token Index: 636

Text #3

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.4100. Min Act: -0.0001

Data Index: 1427041 (Python Code)

Max Activating Token Index: 581

Text #4

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3809. Min Act: -0.0001

Data Index: 1477951 (Python Code)

Max Activating Token Index: 902

Text #5

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3798. Min Act: -0.0001

Data Index: 1575820 (Python Code)

Max Activating Token Index: 368

Text #6

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3800. Min Act: -0.0001

Data Index: 1572997 (Python Code)

Max Activating Token Index: 501

Text #7

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3704. Min Act: -0.0000

Data Index: 1542562 (Python Code)

Max Activating Token Index: 69

Text #8

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3665. Min Act: -0.0000

Data Index: 1466604 (Python Code)

Max Activating Token Index: 497

Text #9

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3562. Min Act: -0.0001

Data Index: 1583667 (Python Code)

Max Activating Token Index: 58

Text #10

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3362. Min Act: -0.0001

Data Index: 1587920 (Python Code)

Max Activating Token Index: 421

Text #11

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3359. Min Act: -0.0001

Data Index: 1609993 (Python Code)

Max Activating Token Index: 315

Text #12

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3450. Min Act: -0.0001

Data Index: 1415042 (Python Code)

Max Activating Token Index: 448

Text #13

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3304. Min Act: -0.0001

Data Index: 1491184 (Python Code)

Max Activating Token Index: 834

Text #14

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3527. Min Act: -0.0001

Data Index: 1647086 (Python Code)

Max Activating Token Index: 311

Text #15

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3366. Min Act: -0.0001

Data Index: 1450326 (Python Code)

Max Activating Token Index: 587

Text #16

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3260. Min Act: -0.0000

Data Index: 1448399 (Python Code)

Max Activating Token Index: 96

Text #17

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3227. Min Act: -0.0001

Data Index: 1605935 (Python Code)

Max Activating Token Index: 750

Text #18

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3339. Min Act: -0.0001

Data Index: 1590208 (Python Code)

Max Activating Token Index: 696

Text #19

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3315. Min Act: -0.0001

Data Index: 1378038 (Python Code)

Max Activating Token Index: 90