Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1524 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.9633. Min Act: -0.0000

Data Index: 178400 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.8967. Min Act: -0.0000

Data Index: 16723 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.8949. Min Act: -0.0001

Data Index: 287301 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.8414. Min Act: -0.0000

Data Index: 575376 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.8327. Min Act: -0.0000

Data Index: 1243319 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.8004. Min Act: -0.0000

Data Index: 13500 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.8440. Min Act: -0.0000

Data Index: 981922 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.8351. Min Act: -0.0000

Data Index: 1303391 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.8887. Min Act: -0.0000

Data Index: 658234 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.8280. Min Act: -0.0001

Data Index: 437753 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.8008. Min Act: -0.0000

Data Index: 1232589 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.7822. Min Act: -0.0000

Data Index: 869577 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.7307. Min Act: -0.0000

Data Index: 597752 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.6867. Min Act: -0.0000

Data Index: 248632 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.7207. Min Act: -0.0000

Data Index: 1137675 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.6987. Min Act: -0.0000

Data Index: 778212 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.7073. Min Act: -0.0000

Data Index: 1320027 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.7033. Min Act: -0.0000

Data Index: 508433 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.7050. Min Act: -0.0001

Data Index: 659662 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.6786. Min Act: -0.0001

Data Index: 1331359 (C4 (Web Text))

Max Activating Token Index: 424