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

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

Neuron 3244 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2409. Min Range: -1.2409

Max Act: 1.2409. Min Act: -0.0001

Data Index: 1266029 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 1.2409. Min Range: -1.2409

Max Act: 1.0170. Min Act: -0.0001

Data Index: 694325 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.9039. Min Act: -0.0001

Data Index: 920182 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.9256. Min Act: -0.0001

Data Index: 1193305 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.8872. Min Act: -0.0001

Data Index: 671303 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.8208. Min Act: -0.0001

Data Index: 1006270 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.8292. Min Act: -0.0001

Data Index: 689419 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.8557. Min Act: -0.0001

Data Index: 150535 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.8342. Min Act: -0.0001

Data Index: 1257425 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.8429. Min Act: -0.0001

Data Index: 898689 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.8017. Min Act: -0.0001

Data Index: 545255 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.8054. Min Act: -0.0001

Data Index: 1062012 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.8445. Min Act: -0.0001

Data Index: 532952 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.8226. Min Act: -0.0001

Data Index: 264937 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.7808. Min Act: -0.0001

Data Index: 544958 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.8146. Min Act: -0.0001

Data Index: 1022634 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.8321. Min Act: -0.0001

Data Index: 742124 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.7516. Min Act: -0.0001

Data Index: 656449 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.7502. Min Act: -0.0001

Data Index: 1111300 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.7878. Min Act: -0.0001

Data Index: 1055365 (C4 (Web Text))

Max Activating Token Index: 205