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

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

Neuron 5533 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3570. Min Range: -3.3570

Max Act: 3.3570. Min Act: -0.0000

Data Index: 460346 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 3.3570. Min Range: -3.3570

Max Act: 3.3316. Min Act: -0.0001

Data Index: 637595 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 3.3570. Min Range: -3.3570

Max Act: 3.1736. Min Act: -0.0000

Data Index: 792891 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 3.3570. Min Range: -3.3570

Max Act: 3.0328. Min Act: -0.0000

Data Index: 170287 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 3.3570. Min Range: -3.3570

Max Act: 3.0910. Min Act: -0.0001

Data Index: 1278007 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 3.3570. Min Range: -3.3570

Max Act: 3.3251. Min Act: -0.0001

Data Index: 33922 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.9174. Min Act: -0.0001

Data Index: 738451 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.8952. Min Act: -0.0000

Data Index: 586599 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 3.3570. Min Range: -3.3570

Max Act: 3.0970. Min Act: -0.0000

Data Index: 163057 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.7198. Min Act: -0.0000

Data Index: 35466 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.6087. Min Act: -0.0001

Data Index: 1094949 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.8037. Min Act: -0.0001

Data Index: 446601 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.7938. Min Act: -0.0001

Data Index: 52252 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.7321. Min Act: -0.0000

Data Index: 88656 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.7191. Min Act: -0.0001

Data Index: 801479 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.6468. Min Act: -0.0000

Data Index: 1188192 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.7114. Min Act: -0.0001

Data Index: 1194510 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.6636. Min Act: -0.0001

Data Index: 1491175 (Python Code)

Max Activating Token Index: 459

Text #18

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.4189. Min Act: -0.0001

Data Index: 1074678 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.4706. Min Act: -0.0000

Data Index: 621609 (C4 (Web Text))

Max Activating Token Index: 773