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

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

Neuron 75 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1586. Min Act: -0.0001

Data Index: 192462 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1658. Min Act: -0.0001

Data Index: 1350660 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1494. Min Act: -0.0001

Data Index: 1351345 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1673. Min Act: -0.0001

Data Index: 1320739 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1591. Min Act: -0.0001

Data Index: 1040488 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1473. Min Act: -0.0001

Data Index: 1246592 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1501. Min Act: -0.0001

Data Index: 978153 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1438. Min Act: -0.0001

Data Index: 152175 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1430. Min Act: -0.0001

Data Index: 382096 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1459. Min Act: -0.0001

Data Index: 558684 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1302. Min Act: -0.0001

Data Index: 232693 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1420. Min Act: -0.0001

Data Index: 258516 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1285. Min Act: -0.0001

Data Index: 397185 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1464. Min Act: -0.0001

Data Index: 411893 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1348. Min Act: -0.0001

Data Index: 731598 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1332. Min Act: -0.0001

Data Index: 962309 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1341. Min Act: -0.0001

Data Index: 507148 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1391. Min Act: -0.0001

Data Index: 337826 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1359. Min Act: -0.0001

Data Index: 414835 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1360. Min Act: -0.0001

Data Index: 1239183 (C4 (Web Text))

Max Activating Token Index: 491