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

Dataset: The Pile

Neuron 2631 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2351. Min Range: -3.2351

Max Act: 3.1813. Min Act: -0.0000

Data Index: 629654 (The Pile)

Max Activating Token Index: 212

Text #1

Max Range: 3.2351. Min Range: -3.2351

Max Act: 2.6998. Min Act: -0.0000

Data Index: 1365819 (The Pile)

Max Activating Token Index: 186

Text #2

Max Range: 3.2351. Min Range: -3.2351

Max Act: 2.8448. Min Act: -0.0000

Data Index: 198067 (The Pile)

Max Activating Token Index: 764

Text #3

Max Range: 3.2351. Min Range: -3.2351

Max Act: 3.0801. Min Act: -0.0000

Data Index: 753573 (The Pile)

Max Activating Token Index: 815

Text #4

Max Range: 3.2351. Min Range: -3.2351

Max Act: 3.2351. Min Act: -0.0000

Data Index: 1507784 (The Pile)

Max Activating Token Index: 261

Text #5

Max Range: 3.2351. Min Range: -3.2351

Max Act: 2.7326. Min Act: -0.0000

Data Index: 404215 (The Pile)

Max Activating Token Index: 159

Text #6

Max Range: 3.2351. Min Range: -3.2351

Max Act: 2.8672. Min Act: -0.0000

Data Index: 697597 (The Pile)

Max Activating Token Index: 517

Text #7

Max Range: 3.2351. Min Range: -3.2351

Max Act: 2.9099. Min Act: -0.0000

Data Index: 328538 (The Pile)

Max Activating Token Index: 950

Text #8

Max Range: 3.2351. Min Range: -3.2351

Max Act: 2.7575. Min Act: -0.0000

Data Index: 14838 (The Pile)

Max Activating Token Index: 387

Text #9

Max Range: 3.2351. Min Range: -3.2351

Max Act: 2.7595. Min Act: -0.0000

Data Index: 1383118 (The Pile)

Max Activating Token Index: 1015

Text #10

Max Range: 3.2351. Min Range: -3.2351

Max Act: 2.7584. Min Act: -0.0000

Data Index: 1189036 (The Pile)

Max Activating Token Index: 809

Text #11

Max Range: 3.2351. Min Range: -3.2351

Max Act: 2.6303. Min Act: -0.0000

Data Index: 825668 (The Pile)

Max Activating Token Index: 878

Text #12

Max Range: 3.2351. Min Range: -3.2351

Max Act: 2.5586. Min Act: -0.0000

Data Index: 26400 (The Pile)

Max Activating Token Index: 273

Text #13

Max Range: 3.2351. Min Range: -3.2351

Max Act: 2.6642. Min Act: -0.0000

Data Index: 139437 (The Pile)

Max Activating Token Index: 203

Text #14

Max Range: 3.2351. Min Range: -3.2351

Max Act: 2.3348. Min Act: -0.0000

Data Index: 385481 (The Pile)

Max Activating Token Index: 168

Text #15

Max Range: 3.2351. Min Range: -3.2351

Max Act: 2.4718. Min Act: -0.0000

Data Index: 712316 (The Pile)

Max Activating Token Index: 758

Text #16

Max Range: 3.2351. Min Range: -3.2351

Max Act: 2.4434. Min Act: -0.0000

Data Index: 1345459 (The Pile)

Max Activating Token Index: 468

Text #17

Max Range: 3.2351. Min Range: -3.2351

Max Act: 2.4197. Min Act: -0.0000

Data Index: 450560 (The Pile)

Max Activating Token Index: 384

Text #18

Max Range: 3.2351. Min Range: -3.2351

Max Act: 2.2831. Min Act: -0.0000

Data Index: 1136185 (The Pile)

Max Activating Token Index: 519

Text #19

Max Range: 3.2351. Min Range: -3.2351

Max Act: 2.2217. Min Act: -0.0000

Data Index: 304502 (The Pile)

Max Activating Token Index: 387