Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3278 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.4750. Min Act: -0.0000

Data Index: 914361 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.4217. Min Act: -0.0000

Data Index: 717551 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.4087. Min Act: -0.0000

Data Index: 267420 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.4055. Min Act: 0.0000

Data Index: 441724 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.4171. Min Act: -0.0000

Data Index: 385072 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3887. Min Act: -0.0000

Data Index: 977486 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3879. Min Act: 0.0000

Data Index: 487678 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3726. Min Act: -0.0000

Data Index: 1293696 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3826. Min Act: -0.0000

Data Index: 404313 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3531. Min Act: -0.0000

Data Index: 566970 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3781. Min Act: -0.0000

Data Index: 1267716 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3562. Min Act: 0.0000

Data Index: 1318464 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3628. Min Act: -0.0000

Data Index: 1182926 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3386. Min Act: -0.0000

Data Index: 810843 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3390. Min Act: -0.0000

Data Index: 1040826 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3398. Min Act: -0.0000

Data Index: 1318914 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3300. Min Act: -0.0000

Data Index: 693428 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3408. Min Act: -0.0000

Data Index: 1309932 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3360. Min Act: -0.0000

Data Index: 282546 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3445. Min Act: -0.0000

Data Index: 415836 (C4 (Web Text))

Max Activating Token Index: 672