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

Dataset: The Pile

Neuron 1782 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: 3.7764. Min Range: -3.7764

Max Act: 3.4752. Min Act: -0.0000

Data Index: 596123 (The Pile)

Max Activating Token Index: 892

Text #1

Max Range: 3.7764. Min Range: -3.7764

Max Act: 3.6148. Min Act: -0.0000

Data Index: 574321 (The Pile)

Max Activating Token Index: 538

Text #2

Max Range: 3.7764. Min Range: -3.7764

Max Act: 3.7764. Min Act: -0.0000

Data Index: 1799533 (The Pile)

Max Activating Token Index: 414

Text #3

Max Range: 3.7764. Min Range: -3.7764

Max Act: 3.6846. Min Act: -0.0000

Data Index: 727799 (The Pile)

Max Activating Token Index: 263

Text #4

Max Range: 3.7764. Min Range: -3.7764

Max Act: 3.7273. Min Act: -0.0000

Data Index: 870357 (The Pile)

Max Activating Token Index: 655

Text #5

Max Range: 3.7764. Min Range: -3.7764

Max Act: 3.7725. Min Act: -0.0000

Data Index: 786263 (The Pile)

Max Activating Token Index: 596

Text #6

Max Range: 3.7764. Min Range: -3.7764

Max Act: 3.6129. Min Act: -0.0000

Data Index: 561103 (The Pile)

Max Activating Token Index: 750

Text #7

Max Range: 3.7764. Min Range: -3.7764

Max Act: 3.2506. Min Act: -0.0000

Data Index: 1774047 (The Pile)

Max Activating Token Index: 770

Text #8

Max Range: 3.7764. Min Range: -3.7764

Max Act: 3.4459. Min Act: -0.0000

Data Index: 310313 (The Pile)

Max Activating Token Index: 511

Text #9

Max Range: 3.7764. Min Range: -3.7764

Max Act: 3.3415. Min Act: -0.0000

Data Index: 365939 (The Pile)

Max Activating Token Index: 679

Text #10

Max Range: 3.7764. Min Range: -3.7764

Max Act: 3.4594. Min Act: -0.0000

Data Index: 1127010 (The Pile)

Max Activating Token Index: 304

Text #11

Max Range: 3.7764. Min Range: -3.7764

Max Act: 3.1972. Min Act: -0.0000

Data Index: 1962954 (The Pile)

Max Activating Token Index: 122

Text #12

Max Range: 3.7764. Min Range: -3.7764

Max Act: 3.3226. Min Act: -0.0000

Data Index: 403596 (The Pile)

Max Activating Token Index: 517

Text #13

Max Range: 3.7764. Min Range: -3.7764

Max Act: 3.2676. Min Act: -0.0000

Data Index: 16895 (The Pile)

Max Activating Token Index: 224

Text #14

Max Range: 3.7764. Min Range: -3.7764

Max Act: 3.4331. Min Act: -0.0000

Data Index: 712727 (The Pile)

Max Activating Token Index: 492

Text #15

Max Range: 3.7764. Min Range: -3.7764

Max Act: 3.2987. Min Act: -0.0000

Data Index: 1351843 (The Pile)

Max Activating Token Index: 295

Text #16

Max Range: 3.7764. Min Range: -3.7764

Max Act: 3.2877. Min Act: -0.0000

Data Index: 1755581 (The Pile)

Max Activating Token Index: 498

Text #17

Max Range: 3.7764. Min Range: -3.7764

Max Act: 3.0390. Min Act: -0.0000

Data Index: 1528663 (The Pile)

Max Activating Token Index: 470

Text #18

Max Range: 3.7764. Min Range: -3.7764

Max Act: 3.2369. Min Act: -0.0000

Data Index: 662642 (The Pile)

Max Activating Token Index: 347

Text #19

Max Range: 3.7764. Min Range: -3.7764

Max Act: 3.0421. Min Act: -0.0000

Data Index: 1936795 (The Pile)

Max Activating Token Index: 518