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

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

Neuron 3670 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6416. Min Range: -2.6416

Max Act: 2.6416. Min Act: -0.0000

Data Index: 1093169 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 2.6416. Min Range: -2.6416

Max Act: 2.2813. Min Act: -0.0000

Data Index: 242968 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 2.6416. Min Range: -2.6416

Max Act: 2.2832. Min Act: -0.0000

Data Index: 196590 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 2.6416. Min Range: -2.6416

Max Act: 2.3876. Min Act: -0.0000

Data Index: 1170983 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 2.6416. Min Range: -2.6416

Max Act: 2.3265. Min Act: -0.0000

Data Index: 9652 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 2.6416. Min Range: -2.6416

Max Act: 2.0929. Min Act: -0.0000

Data Index: 622121 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 2.6416. Min Range: -2.6416

Max Act: 1.7813. Min Act: -0.0000

Data Index: 1025063 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 2.6416. Min Range: -2.6416

Max Act: 1.6856. Min Act: -0.0000

Data Index: 267982 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 2.6416. Min Range: -2.6416

Max Act: 1.8257. Min Act: -0.0000

Data Index: 454381 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 2.6416. Min Range: -2.6416

Max Act: 1.7256. Min Act: -0.0000

Data Index: 584191 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 2.6416. Min Range: -2.6416

Max Act: 1.5645. Min Act: -0.0000

Data Index: 608575 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 2.6416. Min Range: -2.6416

Max Act: 1.5367. Min Act: -0.0000

Data Index: 1225246 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 2.6416. Min Range: -2.6416

Max Act: 1.3682. Min Act: -0.0000

Data Index: 131973 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 2.6416. Min Range: -2.6416

Max Act: 1.5108. Min Act: -0.0000

Data Index: 90036 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 2.6416. Min Range: -2.6416

Max Act: 1.4042. Min Act: -0.0000

Data Index: 44564 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 2.6416. Min Range: -2.6416

Max Act: 1.4073. Min Act: -0.0000

Data Index: 192690 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 2.6416. Min Range: -2.6416

Max Act: 1.4616. Min Act: -0.0000

Data Index: 618569 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 2.6416. Min Range: -2.6416

Max Act: 1.4791. Min Act: -0.0000

Data Index: 1164225 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 2.6416. Min Range: -2.6416

Max Act: 1.4698. Min Act: -0.0000

Data Index: 777788 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 2.6416. Min Range: -2.6416

Max Act: 1.3724. Min Act: -0.0000

Data Index: 1119303 (C4 (Web Text))

Max Activating Token Index: 766