Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 839 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.8624. Min Act: -0.0002

Data Index: 1162730 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.8298. Min Act: -0.0002

Data Index: 1296636 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7992. Min Act: -0.0002

Data Index: 133603 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7808. Min Act: -0.0002

Data Index: 134804 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7553. Min Act: -0.0002

Data Index: 830905 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7448. Min Act: -0.0002

Data Index: 1119995 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7450. Min Act: -0.0002

Data Index: 621077 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7376. Min Act: -0.0002

Data Index: 676707 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7760. Min Act: -0.0002

Data Index: 33107 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7476. Min Act: -0.0002

Data Index: 98450 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7474. Min Act: -0.0002

Data Index: 251993 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7282. Min Act: -0.0002

Data Index: 760987 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7276. Min Act: -0.0002

Data Index: 1045656 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.6895. Min Act: -0.0002

Data Index: 487960 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7281. Min Act: -0.0002

Data Index: 713206 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7707. Min Act: -0.0002

Data Index: 954131 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7122. Min Act: -0.0002

Data Index: 329071 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.6816. Min Act: -0.0002

Data Index: 797943 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.6759. Min Act: -0.0002

Data Index: 1122923 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7082. Min Act: -0.0002

Data Index: 904931 (C4 (Web Text))

Max Activating Token Index: 238