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

Dataset: The Pile

Neuron 3161 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6624. Min Range: -3.6624

Max Act: 3.5691. Min Act: -0.0000

Data Index: 459738 (The Pile)

Max Activating Token Index: 262

Text #1

Max Range: 3.6624. Min Range: -3.6624

Max Act: 3.3836. Min Act: -0.0000

Data Index: 1426199 (The Pile)

Max Activating Token Index: 459

Text #2

Max Range: 3.6624. Min Range: -3.6624

Max Act: 3.5691. Min Act: -0.0000

Data Index: 627330 (The Pile)

Max Activating Token Index: 649

Text #3

Max Range: 3.6624. Min Range: -3.6624

Max Act: 3.6624. Min Act: -0.0000

Data Index: 1122975 (The Pile)

Max Activating Token Index: 851

Text #4

Max Range: 3.6624. Min Range: -3.6624

Max Act: 3.0871. Min Act: -0.0000

Data Index: 301677 (The Pile)

Max Activating Token Index: 605

Text #5

Max Range: 3.6624. Min Range: -3.6624

Max Act: 2.6881. Min Act: -0.0000

Data Index: 148354 (The Pile)

Max Activating Token Index: 388

Text #6

Max Range: 3.6624. Min Range: -3.6624

Max Act: 2.9398. Min Act: -0.0000

Data Index: 775489 (The Pile)

Max Activating Token Index: 89

Text #7

Max Range: 3.6624. Min Range: -3.6624

Max Act: 2.9308. Min Act: -0.0000

Data Index: 326509 (The Pile)

Max Activating Token Index: 592

Text #8

Max Range: 3.6624. Min Range: -3.6624

Max Act: 2.6544. Min Act: -0.0000

Data Index: 1638017 (The Pile)

Max Activating Token Index: 223

Text #9

Max Range: 3.6624. Min Range: -3.6624

Max Act: 2.9016. Min Act: -0.0000

Data Index: 926329 (The Pile)

Max Activating Token Index: 669

Text #10

Max Range: 3.6624. Min Range: -3.6624

Max Act: 2.4989. Min Act: -0.0000

Data Index: 1998710 (The Pile)

Max Activating Token Index: 343

Text #11

Max Range: 3.6624. Min Range: -3.6624

Max Act: 2.7971. Min Act: -0.0000

Data Index: 117762 (The Pile)

Max Activating Token Index: 181

Text #12

Max Range: 3.6624. Min Range: -3.6624

Max Act: 2.4994. Min Act: -0.0000

Data Index: 698920 (The Pile)

Max Activating Token Index: 1009

Text #13

Max Range: 3.6624. Min Range: -3.6624

Max Act: 2.5487. Min Act: -0.0000

Data Index: 1553937 (The Pile)

Max Activating Token Index: 650

Text #14

Max Range: 3.6624. Min Range: -3.6624

Max Act: 2.4260. Min Act: -0.0000

Data Index: 999680 (The Pile)

Max Activating Token Index: 951

Text #15

Max Range: 3.6624. Min Range: -3.6624

Max Act: 2.4106. Min Act: -0.0000

Data Index: 835450 (The Pile)

Max Activating Token Index: 898

Text #16

Max Range: 3.6624. Min Range: -3.6624

Max Act: 2.3854. Min Act: -0.0000

Data Index: 916502 (The Pile)

Max Activating Token Index: 906

Text #17

Max Range: 3.6624. Min Range: -3.6624

Max Act: 2.3141. Min Act: -0.0000

Data Index: 472349 (The Pile)

Max Activating Token Index: 518

Text #18

Max Range: 3.6624. Min Range: -3.6624

Max Act: 2.3879. Min Act: -0.0000

Data Index: 1724498 (The Pile)

Max Activating Token Index: 288

Text #19

Max Range: 3.6624. Min Range: -3.6624

Max Act: 2.3192. Min Act: -0.0000

Data Index: 511040 (The Pile)

Max Activating Token Index: 508