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

Dataset: The Pile

Neuron 4367 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.4350. Min Act: -0.0000

Data Index: 442683 (The Pile)

Max Activating Token Index: 318

Text #1

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.4532. Min Act: -0.0000

Data Index: 1907150 (The Pile)

Max Activating Token Index: 532

Text #2

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.3934. Min Act: -0.0000

Data Index: 1300441 (The Pile)

Max Activating Token Index: 335

Text #3

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.3877. Min Act: -0.0000

Data Index: 383818 (The Pile)

Max Activating Token Index: 112

Text #4

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.2895. Min Act: -0.0000

Data Index: 260546 (The Pile)

Max Activating Token Index: 177

Text #5

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.1967. Min Act: -0.0000

Data Index: 705664 (The Pile)

Max Activating Token Index: 285

Text #6

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.2024. Min Act: -0.0000

Data Index: 1153680 (The Pile)

Max Activating Token Index: 174

Text #7

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.2115. Min Act: -0.0000

Data Index: 653457 (The Pile)

Max Activating Token Index: 349

Text #8

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.2833. Min Act: -0.0000

Data Index: 1326702 (The Pile)

Max Activating Token Index: 29

Text #9

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.2783. Min Act: -0.0000

Data Index: 1906397 (The Pile)

Max Activating Token Index: 340

Text #10

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.2888. Min Act: -0.0000

Data Index: 1622284 (The Pile)

Max Activating Token Index: 35

Text #11

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.2472. Min Act: -0.0000

Data Index: 567124 (The Pile)

Max Activating Token Index: 25

Text #12

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.1999. Min Act: -0.0000

Data Index: 1307505 (The Pile)

Max Activating Token Index: 555

Text #13

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.2547. Min Act: -0.0000

Data Index: 28046 (The Pile)

Max Activating Token Index: 385

Text #14

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.1471. Min Act: -0.0000

Data Index: 473116 (The Pile)

Max Activating Token Index: 188

Text #15

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.1714. Min Act: -0.0000

Data Index: 1133339 (The Pile)

Max Activating Token Index: 252

Text #16

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.2099. Min Act: -0.0000

Data Index: 1068439 (The Pile)

Max Activating Token Index: 130

Text #17

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.1340. Min Act: -0.0000

Data Index: 1441735 (The Pile)

Max Activating Token Index: 26

Text #18

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.1723. Min Act: -0.0000

Data Index: 1046311 (The Pile)

Max Activating Token Index: 463

Text #19

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.0282. Min Act: -0.0000

Data Index: 149147 (The Pile)

Max Activating Token Index: 177