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

Dataset: The Pile

Neuron 2950 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4271. Min Range: -3.4271

Max Act: 3.4271. Min Act: -0.0000

Data Index: 1435400 (The Pile)

Max Activating Token Index: 1002

Text #1

Max Range: 3.4271. Min Range: -3.4271

Max Act: 2.8240. Min Act: 0.0000

Data Index: 1919132 (The Pile)

Max Activating Token Index: 1015

Text #2

Max Range: 3.4271. Min Range: -3.4271

Max Act: 2.8581. Min Act: -0.0000

Data Index: 159231 (The Pile)

Max Activating Token Index: 468

Text #3

Max Range: 3.4271. Min Range: -3.4271

Max Act: 2.5304. Min Act: -0.0000

Data Index: 1763035 (The Pile)

Max Activating Token Index: 624

Text #4

Max Range: 3.4271. Min Range: -3.4271

Max Act: 2.6956. Min Act: -0.0000

Data Index: 1852384 (The Pile)

Max Activating Token Index: 438

Text #5

Max Range: 3.4271. Min Range: -3.4271

Max Act: 2.3711. Min Act: -0.0000

Data Index: 771039 (The Pile)

Max Activating Token Index: 898

Text #6

Max Range: 3.4271. Min Range: -3.4271

Max Act: 2.2517. Min Act: -0.0000

Data Index: 1640425 (The Pile)

Max Activating Token Index: 222

Text #7

Max Range: 3.4271. Min Range: -3.4271

Max Act: 2.6923. Min Act: -0.0000

Data Index: 1073272 (The Pile)

Max Activating Token Index: 1005

Text #8

Max Range: 3.4271. Min Range: -3.4271

Max Act: 2.2153. Min Act: -0.0000

Data Index: 741463 (The Pile)

Max Activating Token Index: 734

Text #9

Max Range: 3.4271. Min Range: -3.4271

Max Act: 2.3820. Min Act: -0.0000

Data Index: 1846401 (The Pile)

Max Activating Token Index: 717

Text #10

Max Range: 3.4271. Min Range: -3.4271

Max Act: 1.9988. Min Act: -0.0000

Data Index: 862020 (The Pile)

Max Activating Token Index: 524

Text #11

Max Range: 3.4271. Min Range: -3.4271

Max Act: 2.0511. Min Act: -0.0000

Data Index: 1877256 (The Pile)

Max Activating Token Index: 333

Text #12

Max Range: 3.4271. Min Range: -3.4271

Max Act: 2.1666. Min Act: -0.0000

Data Index: 384738 (The Pile)

Max Activating Token Index: 843

Text #13

Max Range: 3.4271. Min Range: -3.4271

Max Act: 2.2218. Min Act: -0.0000

Data Index: 307489 (The Pile)

Max Activating Token Index: 982

Text #14

Max Range: 3.4271. Min Range: -3.4271

Max Act: 1.9847. Min Act: -0.0000

Data Index: 452534 (The Pile)

Max Activating Token Index: 422

Text #15

Max Range: 3.4271. Min Range: -3.4271

Max Act: 2.2282. Min Act: -0.0000

Data Index: 1494639 (The Pile)

Max Activating Token Index: 947

Text #16

Max Range: 3.4271. Min Range: -3.4271

Max Act: 2.0362. Min Act: -0.0000

Data Index: 878526 (The Pile)

Max Activating Token Index: 769

Text #17

Max Range: 3.4271. Min Range: -3.4271

Max Act: 1.9628. Min Act: -0.0000

Data Index: 139579 (The Pile)

Max Activating Token Index: 834

Text #18

Max Range: 3.4271. Min Range: -3.4271

Max Act: 1.8092. Min Act: -0.0000

Data Index: 135939 (The Pile)

Max Activating Token Index: 608

Text #19

Max Range: 3.4271. Min Range: -3.4271

Max Act: 1.8600. Min Act: -0.0000

Data Index: 1790175 (The Pile)

Max Activating Token Index: 634