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

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

Neuron 1378 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.6621. Min Act: -0.0001

Data Index: 590110 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.6543. Min Act: -0.0001

Data Index: 1302165 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.6206. Min Act: -0.0001

Data Index: 1271721 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.6072. Min Act: -0.0001

Data Index: 1097352 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.5769. Min Act: -0.0001

Data Index: 991372 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.5721. Min Act: -0.0000

Data Index: 91539 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.5540. Min Act: -0.0001

Data Index: 438066 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4766. Min Act: -0.0000

Data Index: 638556 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.5525. Min Act: -0.0000

Data Index: 704016 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4981. Min Act: -0.0001

Data Index: 309468 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4538. Min Act: -0.0001

Data Index: 342375 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4205. Min Act: -0.0001

Data Index: 1151926 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.3857. Min Act: -0.0000

Data Index: 1339297 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4314. Min Act: -0.0001

Data Index: 1046064 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4303. Min Act: -0.0001

Data Index: 718611 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4219. Min Act: -0.0001

Data Index: 1482386 (Python Code)

Max Activating Token Index: 185

Text #16

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4130. Min Act: -0.0000

Data Index: 1183009 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4107. Min Act: -0.0001

Data Index: 1151995 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4102. Min Act: -0.0001

Data Index: 133322 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.3782. Min Act: -0.0001

Data Index: 511081 (C4 (Web Text))

Max Activating Token Index: 307