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

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

Neuron 2322 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.3679. Min Act: -0.0002

Data Index: 1436796 (Python Code)

Max Activating Token Index: 314

Text #1

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.3891. Min Act: -0.0002

Data Index: 430415 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.3561. Min Act: -0.0002

Data Index: 543460 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.3600. Min Act: -0.0002

Data Index: 935091 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.3421. Min Act: -0.0002

Data Index: 1344004 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.3533. Min Act: -0.0002

Data Index: 523194 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.3504. Min Act: -0.0002

Data Index: 258739 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.3429. Min Act: -0.0002

Data Index: 225880 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.3759. Min Act: -0.0002

Data Index: 18911 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.3483. Min Act: -0.0002

Data Index: 959753 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.3398. Min Act: -0.0002

Data Index: 1578492 (Python Code)

Max Activating Token Index: 504

Text #11

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.3410. Min Act: -0.0002

Data Index: 228780 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.3298. Min Act: -0.0002

Data Index: 385051 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.3507. Min Act: -0.0002

Data Index: 1242328 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.3423. Min Act: -0.0002

Data Index: 1173017 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.3309. Min Act: -0.0002

Data Index: 656897 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.3229. Min Act: -0.0002

Data Index: 1316558 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.3414. Min Act: -0.0002

Data Index: 1235118 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.3290. Min Act: -0.0002

Data Index: 852259 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.2972. Min Act: -0.0002

Data Index: 1177347 (C4 (Web Text))

Max Activating Token Index: 653