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

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

Neuron 2748 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0437. Min Act: -0.0004

Data Index: 1583507 (Python Code)

Max Activating Token Index: 18

Text #1

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0365. Min Act: -0.0003

Data Index: 1485799 (Python Code)

Max Activating Token Index: 725

Text #2

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0338. Min Act: -0.0003

Data Index: 1513561 (Python Code)

Max Activating Token Index: 413

Text #3

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0345. Min Act: -0.0003

Data Index: 292954 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0328. Min Act: -0.0003

Data Index: 1590730 (Python Code)

Max Activating Token Index: 41

Text #5

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0304. Min Act: -0.0003

Data Index: 1318869 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0307. Min Act: -0.0003

Data Index: 1462427 (Python Code)

Max Activating Token Index: 741

Text #7

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0337. Min Act: -0.0003

Data Index: 1583445 (Python Code)

Max Activating Token Index: 38

Text #8

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0311. Min Act: -0.0003

Data Index: 1205118 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0323. Min Act: -0.0003

Data Index: 817170 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0330. Min Act: -0.0004

Data Index: 495964 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0315. Min Act: -0.0003

Data Index: 1323746 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0340. Min Act: -0.0003

Data Index: 62875 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0321. Min Act: -0.0003

Data Index: 1646146 (Python Code)

Max Activating Token Index: 380

Text #14

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0312. Min Act: -0.0003

Data Index: 832473 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0325. Min Act: -0.0003

Data Index: 1507613 (Python Code)

Max Activating Token Index: 453

Text #16

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0298. Min Act: -0.0003

Data Index: 1390315 (Python Code)

Max Activating Token Index: 50

Text #17

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0360. Min Act: -0.0003

Data Index: 1608766 (Python Code)

Max Activating Token Index: 77

Text #18

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0319. Min Act: -0.0003

Data Index: 1271728 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0316. Min Act: -0.0003

Data Index: 701490 (C4 (Web Text))

Max Activating Token Index: 195