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

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

Neuron 1095 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.8624. Min Act: -0.0002

Data Index: 1093923 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.8093. Min Act: -0.0002

Data Index: 968171 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7869. Min Act: -0.0002

Data Index: 1252706 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7648. Min Act: -0.0001

Data Index: 866076 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7760. Min Act: -0.0002

Data Index: 187472 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7367. Min Act: -0.0001

Data Index: 868572 (C4 (Web Text))

Max Activating Token Index: 934

Text #6

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7640. Min Act: -0.0002

Data Index: 711950 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7553. Min Act: -0.0002

Data Index: 51611 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7369. Min Act: -0.0002

Data Index: 132455 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7484. Min Act: -0.0001

Data Index: 180793 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7465. Min Act: -0.0002

Data Index: 1244559 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7310. Min Act: -0.0002

Data Index: 1041585 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7464. Min Act: -0.0002

Data Index: 680353 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7318. Min Act: -0.0001

Data Index: 1116096 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7165. Min Act: -0.0002

Data Index: 101087 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7419. Min Act: -0.0002

Data Index: 1107303 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7205. Min Act: -0.0001

Data Index: 1298516 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7492. Min Act: -0.0002

Data Index: 1081757 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7259. Min Act: -0.0001

Data Index: 1076634 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7568. Min Act: -0.0002

Data Index: 53737 (C4 (Web Text))

Max Activating Token Index: 173