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

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

Neuron 4572 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: 2.4162. Min Range: -2.4162

Max Act: 2.4162. Min Act: -0.0000

Data Index: 71050 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 2.4162. Min Range: -2.4162

Max Act: 2.3789. Min Act: -0.0000

Data Index: 908117 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 2.4162. Min Range: -2.4162

Max Act: 1.6294. Min Act: -0.0000

Data Index: 93086 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 2.4162. Min Range: -2.4162

Max Act: 1.4604. Min Act: -0.0000

Data Index: 493391 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 2.4162. Min Range: -2.4162

Max Act: 1.5296. Min Act: -0.0000

Data Index: 397157 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 2.4162. Min Range: -2.4162

Max Act: 1.4354. Min Act: -0.0000

Data Index: 80409 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 2.4162. Min Range: -2.4162

Max Act: 1.4942. Min Act: -0.0000

Data Index: 698477 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 2.4162. Min Range: -2.4162

Max Act: 1.4866. Min Act: -0.0000

Data Index: 1166163 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 2.4162. Min Range: -2.4162

Max Act: 1.4808. Min Act: -0.0000

Data Index: 646155 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 2.4162. Min Range: -2.4162

Max Act: 1.2986. Min Act: -0.0000

Data Index: 182579 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 2.4162. Min Range: -2.4162

Max Act: 1.3733. Min Act: -0.0000

Data Index: 1129093 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 2.4162. Min Range: -2.4162

Max Act: 1.2780. Min Act: -0.0000

Data Index: 1014914 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 2.4162. Min Range: -2.4162

Max Act: 1.2767. Min Act: -0.0000

Data Index: 364428 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 2.4162. Min Range: -2.4162

Max Act: 1.4256. Min Act: -0.0000

Data Index: 1048111 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 2.4162. Min Range: -2.4162

Max Act: 1.3356. Min Act: -0.0000

Data Index: 1083955 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 2.4162. Min Range: -2.4162

Max Act: 1.4637. Min Act: -0.0000

Data Index: 708514 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 2.4162. Min Range: -2.4162

Max Act: 1.2073. Min Act: -0.0000

Data Index: 934014 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 2.4162. Min Range: -2.4162

Max Act: 1.2886. Min Act: -0.0000

Data Index: 136580 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 2.4162. Min Range: -2.4162

Max Act: 1.3568. Min Act: -0.0000

Data Index: 1146598 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 2.4162. Min Range: -2.4162

Max Act: 1.2737. Min Act: -0.0000

Data Index: 1223009 (C4 (Web Text))

Max Activating Token Index: 33