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

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

Neuron 3130 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6740. Min Range: -5.6740

Max Act: 5.6740. Min Act: -0.0001

Data Index: 2518 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 5.6740. Min Range: -5.6740

Max Act: 4.9281. Min Act: -0.0001

Data Index: 470875 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 5.6740. Min Range: -5.6740

Max Act: 5.0760. Min Act: -0.0001

Data Index: 222717 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 5.6740. Min Range: -5.6740

Max Act: 5.2444. Min Act: -0.0001

Data Index: 639112 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 5.6740. Min Range: -5.6740

Max Act: 4.6391. Min Act: -0.0000

Data Index: 995425 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 5.6740. Min Range: -5.6740

Max Act: 4.6551. Min Act: -0.0001

Data Index: 442834 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 5.6740. Min Range: -5.6740

Max Act: 4.6793. Min Act: -0.0001

Data Index: 1333072 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 5.6740. Min Range: -5.6740

Max Act: 4.8530. Min Act: -0.0001

Data Index: 136715 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 5.6740. Min Range: -5.6740

Max Act: 4.5411. Min Act: -0.0000

Data Index: 1012583 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 5.6740. Min Range: -5.6740

Max Act: 4.5225. Min Act: -0.0001

Data Index: 1246438 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 5.6740. Min Range: -5.6740

Max Act: 4.3861. Min Act: -0.0001

Data Index: 666995 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 5.6740. Min Range: -5.6740

Max Act: 4.4009. Min Act: -0.0001

Data Index: 555117 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 5.6740. Min Range: -5.6740

Max Act: 4.0170. Min Act: -0.0001

Data Index: 157148 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 5.6740. Min Range: -5.6740

Max Act: 3.9478. Min Act: -0.0001

Data Index: 445233 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 5.6740. Min Range: -5.6740

Max Act: 4.0701. Min Act: -0.0001

Data Index: 1279711 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 5.6740. Min Range: -5.6740

Max Act: 4.2362. Min Act: -0.0001

Data Index: 1003522 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 5.6740. Min Range: -5.6740

Max Act: 4.0195. Min Act: -0.0001

Data Index: 1221094 (C4 (Web Text))

Max Activating Token Index: 129

Text #17

Max Range: 5.6740. Min Range: -5.6740

Max Act: 4.1473. Min Act: -0.0000

Data Index: 501578 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 5.6740. Min Range: -5.6740

Max Act: 3.9691. Min Act: -0.0001

Data Index: 722177 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 5.6740. Min Range: -5.6740

Max Act: 4.0499. Min Act: -0.0001

Data Index: 93942 (C4 (Web Text))

Max Activating Token Index: 44