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

Dataset: The Pile

Neuron 2718 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: 4.4541. Min Range: -4.4541

Max Act: 4.4541. Min Act: -0.0000

Data Index: 945769 (The Pile)

Max Activating Token Index: 77

Text #1

Max Range: 4.4541. Min Range: -4.4541

Max Act: 3.6668. Min Act: -0.0000

Data Index: 888206 (The Pile)

Max Activating Token Index: 201

Text #2

Max Range: 4.4541. Min Range: -4.4541

Max Act: 3.6523. Min Act: -0.0000

Data Index: 1187888 (The Pile)

Max Activating Token Index: 417

Text #3

Max Range: 4.4541. Min Range: -4.4541

Max Act: 3.2518. Min Act: -0.0000

Data Index: 922816 (The Pile)

Max Activating Token Index: 681

Text #4

Max Range: 4.4541. Min Range: -4.4541

Max Act: 3.3770. Min Act: -0.0000

Data Index: 1344615 (The Pile)

Max Activating Token Index: 113

Text #5

Max Range: 4.4541. Min Range: -4.4541

Max Act: 3.5637. Min Act: -0.0000

Data Index: 811100 (The Pile)

Max Activating Token Index: 249

Text #6

Max Range: 4.4541. Min Range: -4.4541

Max Act: 3.2873. Min Act: -0.0000

Data Index: 1260054 (The Pile)

Max Activating Token Index: 260

Text #7

Max Range: 4.4541. Min Range: -4.4541

Max Act: 3.3253. Min Act: -0.0000

Data Index: 1301300 (The Pile)

Max Activating Token Index: 680

Text #8

Max Range: 4.4541. Min Range: -4.4541

Max Act: 3.2963. Min Act: -0.0000

Data Index: 1758054 (The Pile)

Max Activating Token Index: 687

Text #9

Max Range: 4.4541. Min Range: -4.4541

Max Act: 3.2910. Min Act: -0.0000

Data Index: 551466 (The Pile)

Max Activating Token Index: 55

Text #10

Max Range: 4.4541. Min Range: -4.4541

Max Act: 3.0866. Min Act: -0.0000

Data Index: 293333 (The Pile)

Max Activating Token Index: 186

Text #11

Max Range: 4.4541. Min Range: -4.4541

Max Act: 3.2326. Min Act: -0.0000

Data Index: 929698 (The Pile)

Max Activating Token Index: 449

Text #12

Max Range: 4.4541. Min Range: -4.4541

Max Act: 3.3334. Min Act: -0.0000

Data Index: 387552 (The Pile)

Max Activating Token Index: 121

Text #13

Max Range: 4.4541. Min Range: -4.4541

Max Act: 3.3017. Min Act: -0.0000

Data Index: 887258 (The Pile)

Max Activating Token Index: 593

Text #14

Max Range: 4.4541. Min Range: -4.4541

Max Act: 3.1148. Min Act: -0.0000

Data Index: 519930 (The Pile)

Max Activating Token Index: 573

Text #15

Max Range: 4.4541. Min Range: -4.4541

Max Act: 2.9899. Min Act: -0.0000

Data Index: 1543956 (The Pile)

Max Activating Token Index: 876

Text #16

Max Range: 4.4541. Min Range: -4.4541

Max Act: 3.0843. Min Act: -0.0000

Data Index: 289904 (The Pile)

Max Activating Token Index: 592

Text #17

Max Range: 4.4541. Min Range: -4.4541

Max Act: 2.9539. Min Act: -0.0000

Data Index: 1860665 (The Pile)

Max Activating Token Index: 537

Text #18

Max Range: 4.4541. Min Range: -4.4541

Max Act: 2.9341. Min Act: -0.0000

Data Index: 351298 (The Pile)

Max Activating Token Index: 634

Text #19

Max Range: 4.4541. Min Range: -4.4541

Max Act: 2.8905. Min Act: -0.0000

Data Index: 197723 (The Pile)

Max Activating Token Index: 331