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

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

Neuron 4750 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: 2.6749. Min Range: -2.6749

Max Act: 2.6749. Min Act: -0.0002

Data Index: 742479 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 2.6749. Min Range: -2.6749

Max Act: 2.6227. Min Act: -0.0002

Data Index: 494939 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 2.6749. Min Range: -2.6749

Max Act: 2.5771. Min Act: -0.0002

Data Index: 944462 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 2.6749. Min Range: -2.6749

Max Act: 2.4664. Min Act: -0.0002

Data Index: 486123 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 2.6749. Min Range: -2.6749

Max Act: 2.4392. Min Act: -0.0002

Data Index: 1276953 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 2.6749. Min Range: -2.6749

Max Act: 2.3570. Min Act: -0.0002

Data Index: 1055687 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 2.6749. Min Range: -2.6749

Max Act: 2.3092. Min Act: -0.0002

Data Index: 47652 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 2.6749. Min Range: -2.6749

Max Act: 2.3574. Min Act: -0.0002

Data Index: 639745 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 2.6749. Min Range: -2.6749

Max Act: 2.3783. Min Act: -0.0002

Data Index: 540475 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 2.6749. Min Range: -2.6749

Max Act: 2.3369. Min Act: -0.0002

Data Index: 1266860 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 2.6749. Min Range: -2.6749

Max Act: 2.3390. Min Act: -0.0002

Data Index: 649829 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 2.6749. Min Range: -2.6749

Max Act: 2.2801. Min Act: -0.0002

Data Index: 10159 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 2.6749. Min Range: -2.6749

Max Act: 2.2724. Min Act: -0.0002

Data Index: 439257 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 2.6749. Min Range: -2.6749

Max Act: 2.2541. Min Act: -0.0002

Data Index: 1089676 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 2.6749. Min Range: -2.6749

Max Act: 2.2499. Min Act: -0.0002

Data Index: 1227893 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 2.6749. Min Range: -2.6749

Max Act: 2.2792. Min Act: -0.0002

Data Index: 705379 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 2.6749. Min Range: -2.6749

Max Act: 2.2636. Min Act: -0.0002

Data Index: 650822 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 2.6749. Min Range: -2.6749

Max Act: 2.2670. Min Act: -0.0002

Data Index: 1254400 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 2.6749. Min Range: -2.6749

Max Act: 2.2516. Min Act: -0.0002

Data Index: 205767 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 2.6749. Min Range: -2.6749

Max Act: 2.2688. Min Act: -0.0002

Data Index: 975430 (C4 (Web Text))

Max Activating Token Index: 443