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

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

Neuron 1450 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.4635. Min Act: -0.0000

Data Index: 1328680 (C4 (Web Text))

Max Activating Token Index: 1018

Text #1

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.3158. Min Act: -0.0000

Data Index: 1081134 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.2651. Min Act: -0.0000

Data Index: 393632 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.1689. Min Act: -0.0000

Data Index: 691783 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.0175. Min Act: -0.0000

Data Index: 130714 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.0341. Min Act: -0.0000

Data Index: 927347 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.0041. Min Act: -0.0000

Data Index: 402725 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.0582. Min Act: -0.0000

Data Index: 413759 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.1331. Min Act: 0.0000

Data Index: 282758 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.0769. Min Act: -0.0000

Data Index: 399329 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.1014. Min Act: -0.0000

Data Index: 335142 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.0023. Min Act: -0.0000

Data Index: 336052 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.0184. Min Act: -0.0000

Data Index: 198914 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 1.4635. Min Range: -1.4635

Max Act: 0.9245. Min Act: -0.0000

Data Index: 1192033 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 1.4635. Min Range: -1.4635

Max Act: 0.9971. Min Act: -0.0000

Data Index: 152387 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.0079. Min Act: -0.0000

Data Index: 624811 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.0048. Min Act: -0.0000

Data Index: 274511 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.0151. Min Act: -0.0000

Data Index: 321 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 1.4635. Min Range: -1.4635

Max Act: 0.9869. Min Act: -0.0000

Data Index: 1208318 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 1.4635. Min Range: -1.4635

Max Act: 0.9777. Min Act: -0.0000

Data Index: 68461 (C4 (Web Text))

Max Activating Token Index: 504