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

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

Neuron 5550 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: 2.0820. Min Range: -2.0820

Max Act: 2.0820. Min Act: -0.0002

Data Index: 382016 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 2.0820. Min Range: -2.0820

Max Act: 2.0499. Min Act: -0.0002

Data Index: 514924 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 2.0820. Min Range: -2.0820

Max Act: 1.9161. Min Act: -0.0002

Data Index: 1305940 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 2.0820. Min Range: -2.0820

Max Act: 1.8739. Min Act: -0.0002

Data Index: 829338 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 2.0820. Min Range: -2.0820

Max Act: 1.7818. Min Act: -0.0002

Data Index: 1146631 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 2.0820. Min Range: -2.0820

Max Act: 1.8486. Min Act: -0.0002

Data Index: 717171 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 2.0820. Min Range: -2.0820

Max Act: 1.8153. Min Act: -0.0002

Data Index: 1055008 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 2.0820. Min Range: -2.0820

Max Act: 1.8426. Min Act: -0.0002

Data Index: 16129 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 2.0820. Min Range: -2.0820

Max Act: 1.7799. Min Act: -0.0002

Data Index: 653772 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 2.0820. Min Range: -2.0820

Max Act: 1.7549. Min Act: -0.0002

Data Index: 1329056 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 2.0820. Min Range: -2.0820

Max Act: 1.8454. Min Act: -0.0002

Data Index: 215896 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 2.0820. Min Range: -2.0820

Max Act: 1.8255. Min Act: -0.0002

Data Index: 859812 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 2.0820. Min Range: -2.0820

Max Act: 1.7612. Min Act: -0.0002

Data Index: 1173973 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 2.0820. Min Range: -2.0820

Max Act: 1.7578. Min Act: -0.0002

Data Index: 222536 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 2.0820. Min Range: -2.0820

Max Act: 1.7059. Min Act: -0.0002

Data Index: 453734 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 2.0820. Min Range: -2.0820

Max Act: 1.7945. Min Act: -0.0002

Data Index: 1133075 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 2.0820. Min Range: -2.0820

Max Act: 1.7226. Min Act: -0.0002

Data Index: 1300399 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 2.0820. Min Range: -2.0820

Max Act: 1.7726. Min Act: -0.0002

Data Index: 1052396 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 2.0820. Min Range: -2.0820

Max Act: 1.6864. Min Act: -0.0002

Data Index: 102594 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 2.0820. Min Range: -2.0820

Max Act: 1.7530. Min Act: -0.0002

Data Index: 918505 (C4 (Web Text))

Max Activating Token Index: 503