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

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

Neuron 3209 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.1585. Min Act: -0.0000

Data Index: 1109010 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.1584. Min Act: -0.0001

Data Index: 1653853 (Python Code)

Max Activating Token Index: 526

Text #2

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.1574. Min Act: -0.0001

Data Index: 181651 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.1544. Min Act: -0.0000

Data Index: 155626 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.1509. Min Act: -0.0000

Data Index: 1086550 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.1429. Min Act: -0.0001

Data Index: 194678 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.1491. Min Act: -0.0000

Data Index: 1035294 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.1525. Min Act: -0.0000

Data Index: 1051663 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.1449. Min Act: -0.0000

Data Index: 639804 (C4 (Web Text))

Max Activating Token Index: 512

Text #9

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.1529. Min Act: -0.0000

Data Index: 976036 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.1397. Min Act: -0.0000

Data Index: 1388126 (Python Code)

Max Activating Token Index: 985

Text #11

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.1435. Min Act: -0.0001

Data Index: 1484003 (Python Code)

Max Activating Token Index: 947

Text #12

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.1277. Min Act: -0.0001

Data Index: 1409617 (Python Code)

Max Activating Token Index: 995

Text #13

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.1358. Min Act: -0.0000

Data Index: 1153230 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.1351. Min Act: -0.0001

Data Index: 666533 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.1306. Min Act: -0.0001

Data Index: 1514851 (Python Code)

Max Activating Token Index: 703

Text #16

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.1358. Min Act: -0.0000

Data Index: 590379 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.1296. Min Act: -0.0000

Data Index: 500787 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.1296. Min Act: -0.0001

Data Index: 1590341 (Python Code)

Max Activating Token Index: 72

Text #19

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.1293. Min Act: -0.0000

Data Index: 1289921 (C4 (Web Text))

Max Activating Token Index: 804