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

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

Neuron 3010 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.8240. Min Act: -0.0001

Data Index: 549220 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6408. Min Act: -0.0001

Data Index: 1275033 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.5286. Min Act: -0.0001

Data Index: 896020 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6868. Min Act: -0.0001

Data Index: 607526 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.5562. Min Act: -0.0001

Data Index: 756476 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.5622. Min Act: -0.0001

Data Index: 1278243 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.5290. Min Act: -0.0001

Data Index: 1056988 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.5376. Min Act: -0.0001

Data Index: 328144 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.5175. Min Act: -0.0001

Data Index: 608911 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.5410. Min Act: -0.0001

Data Index: 72461 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.5126. Min Act: -0.0001

Data Index: 1349773 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.5114. Min Act: -0.0001

Data Index: 1227295 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.5125. Min Act: -0.0001

Data Index: 578270 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.5085. Min Act: -0.0001

Data Index: 200402 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.4737. Min Act: -0.0001

Data Index: 488157 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.5047. Min Act: -0.0001

Data Index: 1176412 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.5014. Min Act: -0.0001

Data Index: 813427 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.5034. Min Act: -0.0001

Data Index: 1379598 (Python Code)

Max Activating Token Index: 271

Text #18

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.5127. Min Act: -0.0001

Data Index: 726065 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.4327. Min Act: -0.0001

Data Index: 391434 (C4 (Web Text))

Max Activating Token Index: 736