Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 651 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.6452. Min Act: -0.0000

Data Index: 1400068 (The Pile)

Max Activating Token Index: 635

Text #1

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.5066. Min Act: -0.0000

Data Index: 1323576 (The Pile)

Max Activating Token Index: 335

Text #2

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.5032. Min Act: -0.0000

Data Index: 177943 (The Pile)

Max Activating Token Index: 424

Text #3

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4910. Min Act: -0.0000

Data Index: 1829660 (The Pile)

Max Activating Token Index: 547

Text #4

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4866. Min Act: -0.0000

Data Index: 630858 (The Pile)

Max Activating Token Index: 206

Text #5

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4876. Min Act: -0.0000

Data Index: 1465630 (The Pile)

Max Activating Token Index: 751

Text #6

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4770. Min Act: -0.0000

Data Index: 1723233 (The Pile)

Max Activating Token Index: 319

Text #7

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4773. Min Act: -0.0000

Data Index: 485358 (The Pile)

Max Activating Token Index: 493

Text #8

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4557. Min Act: -0.0000

Data Index: 914075 (The Pile)

Max Activating Token Index: 118

Text #9

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4458. Min Act: -0.0000

Data Index: 1215843 (The Pile)

Max Activating Token Index: 255

Text #10

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4595. Min Act: -0.0000

Data Index: 1786823 (The Pile)

Max Activating Token Index: 422

Text #11

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4386. Min Act: -0.0000

Data Index: 954409 (The Pile)

Max Activating Token Index: 578

Text #12

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4549. Min Act: -0.0000

Data Index: 910545 (The Pile)

Max Activating Token Index: 278

Text #13

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4516. Min Act: -0.0000

Data Index: 1697903 (The Pile)

Max Activating Token Index: 629

Text #14

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4315. Min Act: -0.0000

Data Index: 1245983 (The Pile)

Max Activating Token Index: 167

Text #15

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4436. Min Act: -0.0000

Data Index: 829505 (The Pile)

Max Activating Token Index: 946

Text #16

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4180. Min Act: -0.0000

Data Index: 524081 (The Pile)

Max Activating Token Index: 445

Text #17

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4172. Min Act: -0.0000

Data Index: 378521 (The Pile)

Max Activating Token Index: 461

Text #18

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4319. Min Act: -0.0000

Data Index: 1081448 (The Pile)

Max Activating Token Index: 538

Text #19

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4208. Min Act: 0.0001

Data Index: 1952889 (The Pile)

Max Activating Token Index: 782