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

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

Neuron 956 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0452. Min Act: -0.0001

Data Index: 1451705 (Python Code)

Max Activating Token Index: 677

Text #1

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0375. Min Act: -0.0001

Data Index: 1465511 (Python Code)

Max Activating Token Index: 458

Text #2

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0362. Min Act: -0.0001

Data Index: 1440149 (Python Code)

Max Activating Token Index: 844

Text #3

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0342. Min Act: -0.0001

Data Index: 1563498 (Python Code)

Max Activating Token Index: 758

Text #4

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0335. Min Act: -0.0001

Data Index: 1417274 (Python Code)

Max Activating Token Index: 715

Text #5

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0330. Min Act: -0.0001

Data Index: 372771 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0344. Min Act: -0.0001

Data Index: 1470175 (Python Code)

Max Activating Token Index: 475

Text #7

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0331. Min Act: -0.0001

Data Index: 1502886 (Python Code)

Max Activating Token Index: 837

Text #8

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0321. Min Act: -0.0001

Data Index: 517183 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0325. Min Act: -0.0001

Data Index: 1408195 (Python Code)

Max Activating Token Index: 804

Text #10

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0335. Min Act: -0.0001

Data Index: 1404490 (Python Code)

Max Activating Token Index: 529

Text #11

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0349. Min Act: -0.0001

Data Index: 1404007 (Python Code)

Max Activating Token Index: 275

Text #12

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0280. Min Act: -0.0001

Data Index: 1412150 (Python Code)

Max Activating Token Index: 897

Text #13

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0323. Min Act: -0.0001

Data Index: 1265936 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0323. Min Act: -0.0001

Data Index: 1571673 (Python Code)

Max Activating Token Index: 408

Text #15

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0329. Min Act: -0.0001

Data Index: 1561144 (Python Code)

Max Activating Token Index: 451

Text #16

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0305. Min Act: -0.0001

Data Index: 1424561 (Python Code)

Max Activating Token Index: 429

Text #17

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0304. Min Act: -0.0001

Data Index: 1546795 (Python Code)

Max Activating Token Index: 944

Text #18

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0307. Min Act: -0.0001

Data Index: 1638250 (Python Code)

Max Activating Token Index: 161

Text #19

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0295. Min Act: -0.0001

Data Index: 1453000 (Python Code)

Max Activating Token Index: 160