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

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

Neuron 1538 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7913. Min Act: -0.0000

Data Index: 922466 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7820. Min Act: -0.0000

Data Index: 1135225 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.8031. Min Act: -0.0000

Data Index: 652600 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7672. Min Act: -0.0000

Data Index: 258490 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7876. Min Act: -0.0000

Data Index: 386690 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7592. Min Act: -0.0000

Data Index: 1355593 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7533. Min Act: -0.0000

Data Index: 905392 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7207. Min Act: -0.0000

Data Index: 882691 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7389. Min Act: -0.0000

Data Index: 1141949 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7442. Min Act: -0.0000

Data Index: 840266 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7459. Min Act: -0.0000

Data Index: 426014 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7146. Min Act: -0.0000

Data Index: 1344943 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7393. Min Act: -0.0000

Data Index: 116359 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7377. Min Act: -0.0000

Data Index: 1071901 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7403. Min Act: -0.0000

Data Index: 504476 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7133. Min Act: -0.0000

Data Index: 92355 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7470. Min Act: -0.0000

Data Index: 118375 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7068. Min Act: -0.0000

Data Index: 385840 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7456. Min Act: -0.0000

Data Index: 250390 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7172. Min Act: -0.0000

Data Index: 1313565 (C4 (Web Text))

Max Activating Token Index: 308