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

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

Neuron 646 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2885. Min Range: -4.2885

Max Act: 4.2885. Min Act: -0.0000

Data Index: 986793 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 4.2885. Min Range: -4.2885

Max Act: 4.0613. Min Act: -0.0000

Data Index: 644627 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 4.2885. Min Range: -4.2885

Max Act: 3.6967. Min Act: -0.0000

Data Index: 123292 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 4.2885. Min Range: -4.2885

Max Act: 3.8336. Min Act: -0.0000

Data Index: 697851 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 4.2885. Min Range: -4.2885

Max Act: 3.3725. Min Act: -0.0000

Data Index: 411182 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 4.2885. Min Range: -4.2885

Max Act: 3.3503. Min Act: -0.0000

Data Index: 1255024 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 4.2885. Min Range: -4.2885

Max Act: 3.4192. Min Act: -0.0000

Data Index: 305365 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 4.2885. Min Range: -4.2885

Max Act: 3.5772. Min Act: -0.0000

Data Index: 713834 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 4.2885. Min Range: -4.2885

Max Act: 3.2526. Min Act: -0.0000

Data Index: 696800 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 4.2885. Min Range: -4.2885

Max Act: 3.3879. Min Act: -0.0000

Data Index: 761741 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 4.2885. Min Range: -4.2885

Max Act: 3.3561. Min Act: -0.0000

Data Index: 84914 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 4.2885. Min Range: -4.2885

Max Act: 3.5176. Min Act: -0.0000

Data Index: 185344 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 4.2885. Min Range: -4.2885

Max Act: 3.2578. Min Act: -0.0000

Data Index: 757318 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 4.2885. Min Range: -4.2885

Max Act: 3.3515. Min Act: -0.0000

Data Index: 1256982 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 4.2885. Min Range: -4.2885

Max Act: 3.1657. Min Act: -0.0000

Data Index: 402572 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 4.2885. Min Range: -4.2885

Max Act: 2.9901. Min Act: -0.0000

Data Index: 827703 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 4.2885. Min Range: -4.2885

Max Act: 2.8877. Min Act: -0.0000

Data Index: 1056527 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 4.2885. Min Range: -4.2885

Max Act: 3.1464. Min Act: -0.0000

Data Index: 238179 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 4.2885. Min Range: -4.2885

Max Act: 3.0022. Min Act: -0.0000

Data Index: 243734 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 4.2885. Min Range: -4.2885

Max Act: 3.1015. Min Act: -0.0000

Data Index: 91790 (C4 (Web Text))

Max Activating Token Index: 785