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

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

Neuron 5823 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5618. Min Range: -2.5618

Max Act: 2.5618. Min Act: -0.0000

Data Index: 384400 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 2.5618. Min Range: -2.5618

Max Act: 2.3209. Min Act: -0.0000

Data Index: 754230 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 2.5618. Min Range: -2.5618

Max Act: 1.9866. Min Act: 0.0000

Data Index: 1176860 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 2.5618. Min Range: -2.5618

Max Act: 1.5970. Min Act: -0.0000

Data Index: 942336 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 2.5618. Min Range: -2.5618

Max Act: 1.5131. Min Act: -0.0000

Data Index: 601532 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 2.5618. Min Range: -2.5618

Max Act: 1.5082. Min Act: -0.0000

Data Index: 1221848 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 2.5618. Min Range: -2.5618

Max Act: 1.4681. Min Act: -0.0000

Data Index: 711905 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 2.5618. Min Range: -2.5618

Max Act: 1.3443. Min Act: -0.0000

Data Index: 278942 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 2.5618. Min Range: -2.5618

Max Act: 1.2608. Min Act: 0.0000

Data Index: 1249573 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 2.5618. Min Range: -2.5618

Max Act: 1.2910. Min Act: -0.0000

Data Index: 1275562 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 2.5618. Min Range: -2.5618

Max Act: 0.9778. Min Act: -0.0000

Data Index: 1245199 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 2.5618. Min Range: -2.5618

Max Act: 1.1930. Min Act: -0.0000

Data Index: 99826 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 2.5618. Min Range: -2.5618

Max Act: 1.1899. Min Act: -0.0000

Data Index: 950357 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 2.5618. Min Range: -2.5618

Max Act: 1.0875. Min Act: -0.0000

Data Index: 563900 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 2.5618. Min Range: -2.5618

Max Act: 1.1549. Min Act: -0.0000

Data Index: 478354 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 2.5618. Min Range: -2.5618

Max Act: 1.1428. Min Act: 0.0001

Data Index: 947389 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 2.5618. Min Range: -2.5618

Max Act: 1.1431. Min Act: -0.0000

Data Index: 106384 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 2.5618. Min Range: -2.5618

Max Act: 1.0550. Min Act: -0.0000

Data Index: 301963 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 2.5618. Min Range: -2.5618

Max Act: 1.1166. Min Act: -0.0000

Data Index: 914537 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 2.5618. Min Range: -2.5618

Max Act: 1.1040. Min Act: -0.0000

Data Index: 861488 (C4 (Web Text))

Max Activating Token Index: 447