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

Dataset: The Pile

Neuron 2584 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: 1.9630. Min Range: -1.9630

Max Act: 1.9630. Min Act: -0.0000

Data Index: 935042 (The Pile)

Max Activating Token Index: 925

Text #1

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.7825. Min Act: -0.0000

Data Index: 1063375 (The Pile)

Max Activating Token Index: 889

Text #2

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.5772. Min Act: -0.0000

Data Index: 898768 (The Pile)

Max Activating Token Index: 1014

Text #3

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.7319. Min Act: -0.0000

Data Index: 1363156 (The Pile)

Max Activating Token Index: 697

Text #4

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.4792. Min Act: -0.0000

Data Index: 1942332 (The Pile)

Max Activating Token Index: 609

Text #5

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.2217. Min Act: -0.0000

Data Index: 62334 (The Pile)

Max Activating Token Index: 972

Text #6

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.7019. Min Act: -0.0000

Data Index: 1535837 (The Pile)

Max Activating Token Index: 461

Text #7

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.6715. Min Act: -0.0000

Data Index: 809347 (The Pile)

Max Activating Token Index: 379

Text #8

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.4833. Min Act: -0.0000

Data Index: 536369 (The Pile)

Max Activating Token Index: 852

Text #9

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.5755. Min Act: -0.0000

Data Index: 38520 (The Pile)

Max Activating Token Index: 234

Text #10

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.5486. Min Act: -0.0000

Data Index: 1757040 (The Pile)

Max Activating Token Index: 596

Text #11

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.3519. Min Act: -0.0000

Data Index: 308167 (The Pile)

Max Activating Token Index: 926

Text #12

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.3891. Min Act: -0.0000

Data Index: 449585 (The Pile)

Max Activating Token Index: 786

Text #13

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.4375. Min Act: -0.0000

Data Index: 31140 (The Pile)

Max Activating Token Index: 329

Text #14

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.3660. Min Act: -0.0000

Data Index: 1509803 (The Pile)

Max Activating Token Index: 466

Text #15

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.4935. Min Act: -0.0000

Data Index: 1824268 (The Pile)

Max Activating Token Index: 96

Text #16

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.5176. Min Act: -0.0000

Data Index: 868146 (The Pile)

Max Activating Token Index: 892

Text #17

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.4178. Min Act: -0.0000

Data Index: 1196331 (The Pile)

Max Activating Token Index: 433

Text #18

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.4007. Min Act: -0.0000

Data Index: 121447 (The Pile)

Max Activating Token Index: 875

Text #19

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.5030. Min Act: -0.0000

Data Index: 1869751 (The Pile)

Max Activating Token Index: 334