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

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

Neuron 2630 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1939. Min Act: 0.0001

Data Index: 774229 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1775. Min Act: -0.0000

Data Index: 935828 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1641. Min Act: 0.0000

Data Index: 886780 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1570. Min Act: 0.0002

Data Index: 551845 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1626. Min Act: -0.0000

Data Index: 1271204 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1555. Min Act: 0.0002

Data Index: 1011753 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1520. Min Act: 0.0000

Data Index: 758030 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1517. Min Act: 0.0002

Data Index: 908414 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1508. Min Act: 0.0001

Data Index: 968505 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1515. Min Act: 0.0001

Data Index: 161293 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1461. Min Act: 0.0001

Data Index: 951709 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1483. Min Act: 0.0000

Data Index: 32200 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1378. Min Act: -0.0000

Data Index: 1042047 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1356. Min Act: 0.0001

Data Index: 525321 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1408. Min Act: 0.0001

Data Index: 95739 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1413. Min Act: 0.0002

Data Index: 971429 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1404. Min Act: 0.0002

Data Index: 318783 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1387. Min Act: 0.0000

Data Index: 1010123 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1345. Min Act: 0.0001

Data Index: 919801 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1325. Min Act: 0.0000

Data Index: 587548 (C4 (Web Text))

Max Activating Token Index: 152