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

Dataset: The Pile

Neuron 2384 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: 1.0768. Min Range: -1.0768

Max Act: 1.0768. Min Act: -0.0000

Data Index: 609199 (The Pile)

Max Activating Token Index: 227

Text #1

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.9546. Min Act: -0.0000

Data Index: 1433676 (The Pile)

Max Activating Token Index: 422

Text #2

Max Range: 1.0768. Min Range: -1.0768

Max Act: 1.0359. Min Act: -0.0000

Data Index: 717059 (The Pile)

Max Activating Token Index: 1008

Text #3

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.8571. Min Act: -0.0000

Data Index: 1311866 (The Pile)

Max Activating Token Index: 529

Text #4

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.8725. Min Act: -0.0000

Data Index: 1142733 (The Pile)

Max Activating Token Index: 306

Text #5

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.8473. Min Act: -0.0000

Data Index: 1380471 (The Pile)

Max Activating Token Index: 50

Text #6

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.8505. Min Act: -0.0000

Data Index: 1436292 (The Pile)

Max Activating Token Index: 487

Text #7

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7738. Min Act: -0.0000

Data Index: 907146 (The Pile)

Max Activating Token Index: 32

Text #8

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7336. Min Act: -0.0000

Data Index: 1799533 (The Pile)

Max Activating Token Index: 30

Text #9

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7950. Min Act: -0.0000

Data Index: 1555846 (The Pile)

Max Activating Token Index: 234

Text #10

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7750. Min Act: -0.0000

Data Index: 119831 (The Pile)

Max Activating Token Index: 820

Text #11

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7651. Min Act: -0.0000

Data Index: 634549 (The Pile)

Max Activating Token Index: 199

Text #12

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7414. Min Act: -0.0000

Data Index: 1456921 (The Pile)

Max Activating Token Index: 45

Text #13

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7270. Min Act: -0.0000

Data Index: 1268656 (The Pile)

Max Activating Token Index: 883

Text #14

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7189. Min Act: -0.0000

Data Index: 1085432 (The Pile)

Max Activating Token Index: 792

Text #15

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7663. Min Act: -0.0000

Data Index: 86020 (The Pile)

Max Activating Token Index: 320

Text #16

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7187. Min Act: -0.0000

Data Index: 17407 (The Pile)

Max Activating Token Index: 368

Text #17

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7353. Min Act: -0.0000

Data Index: 1865919 (The Pile)

Max Activating Token Index: 211

Text #18

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.6929. Min Act: -0.0000

Data Index: 1178939 (The Pile)

Max Activating Token Index: 255

Text #19

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7256. Min Act: -0.0000

Data Index: 164606 (The Pile)

Max Activating Token Index: 740