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

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

Neuron 1195 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.5959. Min Act: -0.0002

Data Index: 1305760 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.5339. Min Act: -0.0002

Data Index: 231177 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.5152. Min Act: -0.0002

Data Index: 779800 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.5024. Min Act: -0.0002

Data Index: 599330 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.4712. Min Act: -0.0002

Data Index: 965065 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.4712. Min Act: -0.0002

Data Index: 31509 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.4669. Min Act: -0.0002

Data Index: 1216303 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.4724. Min Act: -0.0002

Data Index: 266183 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.4699. Min Act: -0.0002

Data Index: 50204 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.4694. Min Act: -0.0002

Data Index: 898281 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.4635. Min Act: -0.0002

Data Index: 800846 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.4595. Min Act: -0.0002

Data Index: 726 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.4613. Min Act: -0.0002

Data Index: 336220 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.4557. Min Act: -0.0002

Data Index: 329937 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.4532. Min Act: -0.0002

Data Index: 1084208 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.4588. Min Act: -0.0002

Data Index: 747881 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.4521. Min Act: -0.0002

Data Index: 559796 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.4494. Min Act: -0.0002

Data Index: 1306683 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.4491. Min Act: -0.0002

Data Index: 809161 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.4491. Min Act: -0.0002

Data Index: 1143511 (C4 (Web Text))

Max Activating Token Index: 17