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

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

Neuron 1328 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0550. Min Act: -0.0000

Data Index: 1568649 (Python Code)

Max Activating Token Index: 654

Text #1

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0432. Min Act: -0.0000

Data Index: 1558359 (Python Code)

Max Activating Token Index: 887

Text #2

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0395. Min Act: -0.0000

Data Index: 515648 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0387. Min Act: -0.0000

Data Index: 746442 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0362. Min Act: -0.0000

Data Index: 11346 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0350. Min Act: -0.0000

Data Index: 1014043 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0316. Min Act: -0.0000

Data Index: 352131 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0329. Min Act: -0.0000

Data Index: 861488 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0339. Min Act: -0.0000

Data Index: 502045 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0358. Min Act: -0.0000

Data Index: 1455696 (Python Code)

Max Activating Token Index: 899

Text #10

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0310. Min Act: -0.0000

Data Index: 461338 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0311. Min Act: -0.0000

Data Index: 1340346 (C4 (Web Text))

Max Activating Token Index: 959

Text #12

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0321. Min Act: -0.0000

Data Index: 19474 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0327. Min Act: -0.0000

Data Index: 654084 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0316. Min Act: -0.0000

Data Index: 1061197 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0316. Min Act: -0.0000

Data Index: 884551 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0319. Min Act: -0.0000

Data Index: 1116887 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0310. Min Act: -0.0000

Data Index: 1213558 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0321. Min Act: -0.0000

Data Index: 233277 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0296. Min Act: -0.0000

Data Index: 302383 (C4 (Web Text))

Max Activating Token Index: 994