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

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

Neuron 3659 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0212. Min Range: -5.0212

Max Act: 4.8913. Min Act: -0.0001

Data Index: 553746 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 5.0212. Min Range: -5.0212

Max Act: 4.7079. Min Act: -0.0001

Data Index: 1128411 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 5.0212. Min Range: -5.0212

Max Act: 4.7097. Min Act: -0.0001

Data Index: 251787 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 5.0212. Min Range: -5.0212

Max Act: 5.0212. Min Act: -0.0001

Data Index: 680952 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 5.0212. Min Range: -5.0212

Max Act: 4.6731. Min Act: -0.0001

Data Index: 277901 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 5.0212. Min Range: -5.0212

Max Act: 4.1697. Min Act: -0.0001

Data Index: 1069199 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 5.0212. Min Range: -5.0212

Max Act: 4.1929. Min Act: -0.0001

Data Index: 1153775 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 5.0212. Min Range: -5.0212

Max Act: 4.6684. Min Act: -0.0001

Data Index: 103016 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 5.0212. Min Range: -5.0212

Max Act: 4.2893. Min Act: -0.0001

Data Index: 1139200 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 5.0212. Min Range: -5.0212

Max Act: 4.0089. Min Act: -0.0001

Data Index: 517529 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 5.0212. Min Range: -5.0212

Max Act: 4.0798. Min Act: -0.0001

Data Index: 944606 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 5.0212. Min Range: -5.0212

Max Act: 3.6132. Min Act: -0.0001

Data Index: 468071 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 5.0212. Min Range: -5.0212

Max Act: 3.8655. Min Act: -0.0001

Data Index: 357693 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 5.0212. Min Range: -5.0212

Max Act: 4.1430. Min Act: -0.0001

Data Index: 377072 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 5.0212. Min Range: -5.0212

Max Act: 3.8207. Min Act: -0.0001

Data Index: 672122 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 5.0212. Min Range: -5.0212

Max Act: 4.1447. Min Act: -0.0001

Data Index: 1030304 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 5.0212. Min Range: -5.0212

Max Act: 3.6253. Min Act: -0.0001

Data Index: 199976 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 5.0212. Min Range: -5.0212

Max Act: 4.0927. Min Act: -0.0001

Data Index: 805290 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 5.0212. Min Range: -5.0212

Max Act: 4.1711. Min Act: -0.0001

Data Index: 5575 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 5.0212. Min Range: -5.0212

Max Act: 3.5819. Min Act: -0.0001

Data Index: 968017 (C4 (Web Text))

Max Activating Token Index: 832