Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 569 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.5516. Min Act: -0.0000

Data Index: 784873 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.5262. Min Act: -0.0000

Data Index: 596991 (C4 (Web Text))

Max Activating Token Index: 478

Text #2

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.5576. Min Act: -0.0000

Data Index: 665384 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.5381. Min Act: -0.0000

Data Index: 1244239 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.5069. Min Act: -0.0000

Data Index: 317272 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.4735. Min Act: -0.0000

Data Index: 1227280 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.4830. Min Act: -0.0000

Data Index: 587195 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.5014. Min Act: -0.0000

Data Index: 196278 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.4983. Min Act: -0.0000

Data Index: 276049 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.4566. Min Act: -0.0000

Data Index: 716079 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.4389. Min Act: -0.0000

Data Index: 400747 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.4503. Min Act: -0.0000

Data Index: 538534 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.3890. Min Act: -0.0000

Data Index: 1449712 (Python Code)

Max Activating Token Index: 199

Text #13

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.4154. Min Act: -0.0000

Data Index: 872658 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.4140. Min Act: -0.0000

Data Index: 939022 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.4163. Min Act: -0.0000

Data Index: 975293 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.3959. Min Act: -0.0000

Data Index: 1356816 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.3772. Min Act: -0.0000

Data Index: 690853 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.3983. Min Act: -0.0000

Data Index: 1229097 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.4200. Min Act: -0.0000

Data Index: 841236 (C4 (Web Text))

Max Activating Token Index: 68