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

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

Neuron 2531 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0434. Min Range: -2.0434

Max Act: 2.0434. Min Act: -0.0000

Data Index: 932208 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 2.0434. Min Range: -2.0434

Max Act: 1.8911. Min Act: 0.0001

Data Index: 1055464 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 2.0434. Min Range: -2.0434

Max Act: 1.7596. Min Act: -0.0000

Data Index: 1133601 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 2.0434. Min Range: -2.0434

Max Act: 1.7058. Min Act: -0.0000

Data Index: 463603 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 2.0434. Min Range: -2.0434

Max Act: 1.7917. Min Act: -0.0000

Data Index: 1261595 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 2.0434. Min Range: -2.0434

Max Act: 1.6513. Min Act: 0.0000

Data Index: 1281265 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 2.0434. Min Range: -2.0434

Max Act: 1.7401. Min Act: -0.0000

Data Index: 751669 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 2.0434. Min Range: -2.0434

Max Act: 1.7125. Min Act: -0.0000

Data Index: 181280 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 2.0434. Min Range: -2.0434

Max Act: 1.7318. Min Act: -0.0000

Data Index: 26639 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 2.0434. Min Range: -2.0434

Max Act: 1.6377. Min Act: -0.0000

Data Index: 76140 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 2.0434. Min Range: -2.0434

Max Act: 1.5805. Min Act: -0.0000

Data Index: 1008362 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 2.0434. Min Range: -2.0434

Max Act: 1.6717. Min Act: -0.0000

Data Index: 6434 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 2.0434. Min Range: -2.0434

Max Act: 1.7694. Min Act: -0.0000

Data Index: 608713 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 2.0434. Min Range: -2.0434

Max Act: 1.6414. Min Act: -0.0000

Data Index: 924142 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 2.0434. Min Range: -2.0434

Max Act: 1.7157. Min Act: -0.0000

Data Index: 1068141 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 2.0434. Min Range: -2.0434

Max Act: 1.6251. Min Act: -0.0000

Data Index: 1301826 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 2.0434. Min Range: -2.0434

Max Act: 1.6249. Min Act: -0.0000

Data Index: 622799 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 2.0434. Min Range: -2.0434

Max Act: 1.7055. Min Act: -0.0000

Data Index: 168429 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 2.0434. Min Range: -2.0434

Max Act: 1.4823. Min Act: -0.0000

Data Index: 394240 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 2.0434. Min Range: -2.0434

Max Act: 1.4824. Min Act: -0.0000

Data Index: 501928 (C4 (Web Text))

Max Activating Token Index: 258