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

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

Neuron 4200 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: 3.0076. Min Range: -3.0076

Max Act: 2.9411. Min Act: -0.0003

Data Index: 82288 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 3.0076. Min Range: -3.0076

Max Act: 2.9095. Min Act: -0.0002

Data Index: 74519 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 3.0076. Min Range: -3.0076

Max Act: 3.0076. Min Act: -0.0002

Data Index: 1059330 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 3.0076. Min Range: -3.0076

Max Act: 2.8456. Min Act: -0.0002

Data Index: 1309009 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 3.0076. Min Range: -3.0076

Max Act: 2.9030. Min Act: -0.0002

Data Index: 139659 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 3.0076. Min Range: -3.0076

Max Act: 2.7882. Min Act: -0.0002

Data Index: 1159655 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 3.0076. Min Range: -3.0076

Max Act: 2.7369. Min Act: -0.0003

Data Index: 102956 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 3.0076. Min Range: -3.0076

Max Act: 2.6959. Min Act: -0.0002

Data Index: 1109924 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 3.0076. Min Range: -3.0076

Max Act: 2.6654. Min Act: -0.0002

Data Index: 1092559 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 3.0076. Min Range: -3.0076

Max Act: 2.7032. Min Act: -0.0002

Data Index: 259854 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 3.0076. Min Range: -3.0076

Max Act: 2.7231. Min Act: -0.0002

Data Index: 662272 (C4 (Web Text))

Max Activating Token Index: 566

Text #11

Max Range: 3.0076. Min Range: -3.0076

Max Act: 2.6933. Min Act: -0.0002

Data Index: 1290380 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 3.0076. Min Range: -3.0076

Max Act: 2.5991. Min Act: -0.0002

Data Index: 593358 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 3.0076. Min Range: -3.0076

Max Act: 2.6077. Min Act: -0.0002

Data Index: 26881 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 3.0076. Min Range: -3.0076

Max Act: 2.6907. Min Act: -0.0003

Data Index: 757857 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 3.0076. Min Range: -3.0076

Max Act: 2.6426. Min Act: -0.0002

Data Index: 454333 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 3.0076. Min Range: -3.0076

Max Act: 2.6657. Min Act: -0.0002

Data Index: 1227949 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 3.0076. Min Range: -3.0076

Max Act: 2.5718. Min Act: -0.0002

Data Index: 819866 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 3.0076. Min Range: -3.0076

Max Act: 2.6280. Min Act: -0.0002

Data Index: 241376 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 3.0076. Min Range: -3.0076

Max Act: 2.5958. Min Act: -0.0002

Data Index: 390730 (C4 (Web Text))

Max Activating Token Index: 589