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

Dataset: The Pile

Neuron 2450 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3633. Min Range: -5.3633

Max Act: 5.3633. Min Act: -0.0000

Data Index: 1903266 (The Pile)

Max Activating Token Index: 441

Text #1

Max Range: 5.3633. Min Range: -5.3633

Max Act: 5.3562. Min Act: -0.0000

Data Index: 1052800 (The Pile)

Max Activating Token Index: 769

Text #2

Max Range: 5.3633. Min Range: -5.3633

Max Act: 4.9465. Min Act: -0.0000

Data Index: 1831043 (The Pile)

Max Activating Token Index: 441

Text #3

Max Range: 5.3633. Min Range: -5.3633

Max Act: 5.0701. Min Act: -0.0000

Data Index: 163882 (The Pile)

Max Activating Token Index: 443

Text #4

Max Range: 5.3633. Min Range: -5.3633

Max Act: 4.8520. Min Act: -0.0000

Data Index: 1737881 (The Pile)

Max Activating Token Index: 121

Text #5

Max Range: 5.3633. Min Range: -5.3633

Max Act: 4.9601. Min Act: -0.0000

Data Index: 790426 (The Pile)

Max Activating Token Index: 279

Text #6

Max Range: 5.3633. Min Range: -5.3633

Max Act: 4.8054. Min Act: -0.0000

Data Index: 779612 (The Pile)

Max Activating Token Index: 376

Text #7

Max Range: 5.3633. Min Range: -5.3633

Max Act: 4.4487. Min Act: -0.0000

Data Index: 1155942 (The Pile)

Max Activating Token Index: 332

Text #8

Max Range: 5.3633. Min Range: -5.3633

Max Act: 4.2916. Min Act: -0.0000

Data Index: 23484 (The Pile)

Max Activating Token Index: 545

Text #9

Max Range: 5.3633. Min Range: -5.3633

Max Act: 4.2525. Min Act: -0.0000

Data Index: 324823 (The Pile)

Max Activating Token Index: 83

Text #10

Max Range: 5.3633. Min Range: -5.3633

Max Act: 4.0226. Min Act: -0.0000

Data Index: 1298001 (The Pile)

Max Activating Token Index: 893

Text #11

Max Range: 5.3633. Min Range: -5.3633

Max Act: 4.6638. Min Act: -0.0000

Data Index: 546960 (The Pile)

Max Activating Token Index: 347

Text #12

Max Range: 5.3633. Min Range: -5.3633

Max Act: 4.8075. Min Act: -0.0000

Data Index: 875651 (The Pile)

Max Activating Token Index: 747

Text #13

Max Range: 5.3633. Min Range: -5.3633

Max Act: 4.4132. Min Act: -0.0000

Data Index: 389689 (The Pile)

Max Activating Token Index: 429

Text #14

Max Range: 5.3633. Min Range: -5.3633

Max Act: 4.9170. Min Act: -0.0000

Data Index: 1600544 (The Pile)

Max Activating Token Index: 247

Text #15

Max Range: 5.3633. Min Range: -5.3633

Max Act: 4.3154. Min Act: -0.0000

Data Index: 134234 (The Pile)

Max Activating Token Index: 387

Text #16

Max Range: 5.3633. Min Range: -5.3633

Max Act: 4.5048. Min Act: -0.0000

Data Index: 17725 (The Pile)

Max Activating Token Index: 171

Text #17

Max Range: 5.3633. Min Range: -5.3633

Max Act: 4.3345. Min Act: -0.0000

Data Index: 1817384 (The Pile)

Max Activating Token Index: 739

Text #18

Max Range: 5.3633. Min Range: -5.3633

Max Act: 3.9332. Min Act: -0.0000

Data Index: 1245128 (The Pile)

Max Activating Token Index: 653

Text #19

Max Range: 5.3633. Min Range: -5.3633

Max Act: 3.7294. Min Act: -0.0000

Data Index: 316515 (The Pile)

Max Activating Token Index: 740