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

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

Neuron 23 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.9485. Min Act: -0.0001

Data Index: 555355 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.9288. Min Act: -0.0001

Data Index: 1336464 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.7901. Min Act: -0.0000

Data Index: 209176 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.8108. Min Act: -0.0000

Data Index: 681971 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.7803. Min Act: -0.0000

Data Index: 411285 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.7807. Min Act: -0.0000

Data Index: 224033 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.7435. Min Act: -0.0000

Data Index: 1118202 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.6872. Min Act: -0.0001

Data Index: 465252 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.6743. Min Act: -0.0000

Data Index: 1274707 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.6897. Min Act: -0.0000

Data Index: 1269076 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.6851. Min Act: -0.0000

Data Index: 107906 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.6883. Min Act: -0.0001

Data Index: 1016408 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.6758. Min Act: -0.0001

Data Index: 1213018 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.6973. Min Act: -0.0000

Data Index: 1124462 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.6708. Min Act: -0.0001

Data Index: 412080 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.6453. Min Act: -0.0001

Data Index: 114638 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.6807. Min Act: -0.0000

Data Index: 345078 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.6781. Min Act: -0.0001

Data Index: 63837 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.6777. Min Act: -0.0001

Data Index: 291915 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.6550. Min Act: -0.0001

Data Index: 552019 (C4 (Web Text))

Max Activating Token Index: 689