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

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

Neuron 3150 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0524. Min Act: -0.0002

Data Index: 1200189 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0487. Min Act: -0.0002

Data Index: 93428 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0501. Min Act: -0.0002

Data Index: 695097 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0478. Min Act: -0.0002

Data Index: 442403 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0474. Min Act: -0.0002

Data Index: 270338 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0468. Min Act: -0.0002

Data Index: 1256559 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0471. Min Act: -0.0002

Data Index: 880723 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0471. Min Act: -0.0002

Data Index: 586621 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0476. Min Act: -0.0002

Data Index: 144536 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0482. Min Act: -0.0002

Data Index: 688603 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0455. Min Act: -0.0002

Data Index: 1271081 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0468. Min Act: -0.0002

Data Index: 955030 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0473. Min Act: -0.0002

Data Index: 292477 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0455. Min Act: -0.0002

Data Index: 1314780 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0453. Min Act: -0.0002

Data Index: 1015719 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0465. Min Act: -0.0002

Data Index: 424839 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0455. Min Act: -0.0002

Data Index: 822478 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0443. Min Act: -0.0002

Data Index: 881279 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1110949 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0461. Min Act: -0.0002

Data Index: 1246585 (C4 (Web Text))

Max Activating Token Index: 339