Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3414 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.2325. Min Act: 0.0000

Data Index: 1190106 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.2255. Min Act: -0.0000

Data Index: 1274992 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.2162. Min Act: -0.0000

Data Index: 484672 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.2042. Min Act: -0.0000

Data Index: 976090 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.2203. Min Act: -0.0000

Data Index: 1624 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.2001. Min Act: -0.0000

Data Index: 436618 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1747. Min Act: -0.0000

Data Index: 687618 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1801. Min Act: -0.0000

Data Index: 578785 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1675. Min Act: -0.0000

Data Index: 514749 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1621. Min Act: -0.0000

Data Index: 407706 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1667. Min Act: -0.0000

Data Index: 1327557 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1520. Min Act: -0.0000

Data Index: 1283714 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1470. Min Act: -0.0000

Data Index: 540903 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1462. Min Act: -0.0000

Data Index: 1033573 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1441. Min Act: -0.0000

Data Index: 946769 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1432. Min Act: -0.0000

Data Index: 520814 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1412. Min Act: -0.0000

Data Index: 688420 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1421. Min Act: -0.0000

Data Index: 1111815 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1455. Min Act: -0.0000

Data Index: 482378 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1448. Min Act: -0.0000

Data Index: 179737 (C4 (Web Text))

Max Activating Token Index: 696