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

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

Neuron 3802 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4074. Min Range: -2.4074

Max Act: 2.3319. Min Act: -0.0000

Data Index: 1027707 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 2.4074. Min Range: -2.4074

Max Act: 2.4074. Min Act: -0.0000

Data Index: 791921 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 2.4074. Min Range: -2.4074

Max Act: 1.9400. Min Act: -0.0000

Data Index: 513036 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 2.4074. Min Range: -2.4074

Max Act: 1.9285. Min Act: -0.0000

Data Index: 277653 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 2.4074. Min Range: -2.4074

Max Act: 1.8963. Min Act: -0.0000

Data Index: 468111 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 2.4074. Min Range: -2.4074

Max Act: 1.7035. Min Act: -0.0000

Data Index: 1238354 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 2.4074. Min Range: -2.4074

Max Act: 1.6010. Min Act: -0.0000

Data Index: 266776 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 2.4074. Min Range: -2.4074

Max Act: 1.6558. Min Act: -0.0000

Data Index: 808719 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 2.4074. Min Range: -2.4074

Max Act: 1.6004. Min Act: -0.0000

Data Index: 875633 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 2.4074. Min Range: -2.4074

Max Act: 1.5891. Min Act: -0.0000

Data Index: 601844 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 2.4074. Min Range: -2.4074

Max Act: 1.4725. Min Act: -0.0000

Data Index: 512464 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 2.4074. Min Range: -2.4074

Max Act: 1.6255. Min Act: -0.0000

Data Index: 1166064 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 2.4074. Min Range: -2.4074

Max Act: 1.5294. Min Act: -0.0000

Data Index: 53319 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 2.4074. Min Range: -2.4074

Max Act: 1.6096. Min Act: -0.0000

Data Index: 1177426 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 2.4074. Min Range: -2.4074

Max Act: 1.5251. Min Act: -0.0000

Data Index: 310070 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 2.4074. Min Range: -2.4074

Max Act: 1.4956. Min Act: -0.0000

Data Index: 1270457 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 2.4074. Min Range: -2.4074

Max Act: 1.3349. Min Act: -0.0000

Data Index: 953755 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 2.4074. Min Range: -2.4074

Max Act: 1.4014. Min Act: -0.0000

Data Index: 880411 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 2.4074. Min Range: -2.4074

Max Act: 1.3953. Min Act: -0.0000

Data Index: 220597 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 2.4074. Min Range: -2.4074

Max Act: 1.3107. Min Act: -0.0000

Data Index: 143534 (C4 (Web Text))

Max Activating Token Index: 936