Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 255 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0666. Min Act: -0.0003

Data Index: 423917 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0527. Min Act: -0.0003

Data Index: 1656186 (Python Code)

Max Activating Token Index: 858

Text #2

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0507. Min Act: -0.0004

Data Index: 179271 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0495. Min Act: -0.0003

Data Index: 1119777 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0472. Min Act: -0.0003

Data Index: 353704 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0456. Min Act: -0.0003

Data Index: 1180245 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0468. Min Act: -0.0003

Data Index: 446059 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0466. Min Act: -0.0003

Data Index: 931088 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0438. Min Act: -0.0003

Data Index: 1209680 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0445. Min Act: -0.0004

Data Index: 1203877 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0446. Min Act: -0.0003

Data Index: 123037 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0442. Min Act: -0.0003

Data Index: 732605 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0429. Min Act: -0.0003

Data Index: 585202 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0431. Min Act: -0.0003

Data Index: 1583937 (Python Code)

Max Activating Token Index: 684

Text #14

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0442. Min Act: -0.0003

Data Index: 1411367 (Python Code)

Max Activating Token Index: 540

Text #15

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0437. Min Act: -0.0003

Data Index: 127308 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0438. Min Act: -0.0003

Data Index: 699426 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0429. Min Act: -0.0003

Data Index: 694945 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0435. Min Act: -0.0003

Data Index: 1312614 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0435. Min Act: -0.0004

Data Index: 971530 (C4 (Web Text))

Max Activating Token Index: 47