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

Dataset: The Pile

Neuron 14 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: 5.9177. Min Range: -5.9177

Max Act: 5.9177. Min Act: -0.0000

Data Index: 785005 (The Pile)

Max Activating Token Index: 10

Text #1

Max Range: 5.9177. Min Range: -5.9177

Max Act: 5.4532. Min Act: -0.0000

Data Index: 1355963 (The Pile)

Max Activating Token Index: 555

Text #2

Max Range: 5.9177. Min Range: -5.9177

Max Act: 5.4011. Min Act: -0.0000

Data Index: 840076 (The Pile)

Max Activating Token Index: 599

Text #3

Max Range: 5.9177. Min Range: -5.9177

Max Act: 5.3458. Min Act: -0.0000

Data Index: 731636 (The Pile)

Max Activating Token Index: 47

Text #4

Max Range: 5.9177. Min Range: -5.9177

Max Act: 5.3143. Min Act: -0.0000

Data Index: 145952 (The Pile)

Max Activating Token Index: 450

Text #5

Max Range: 5.9177. Min Range: -5.9177

Max Act: 4.8498. Min Act: -0.0000

Data Index: 1432515 (The Pile)

Max Activating Token Index: 696

Text #6

Max Range: 5.9177. Min Range: -5.9177

Max Act: 5.0655. Min Act: -0.0000

Data Index: 1763727 (The Pile)

Max Activating Token Index: 143

Text #7

Max Range: 5.9177. Min Range: -5.9177

Max Act: 4.8302. Min Act: -0.0000

Data Index: 1094479 (The Pile)

Max Activating Token Index: 848

Text #8

Max Range: 5.9177. Min Range: -5.9177

Max Act: 5.1357. Min Act: -0.0000

Data Index: 738685 (The Pile)

Max Activating Token Index: 23

Text #9

Max Range: 5.9177. Min Range: -5.9177

Max Act: 4.5958. Min Act: -0.0000

Data Index: 1936573 (The Pile)

Max Activating Token Index: 300

Text #10

Max Range: 5.9177. Min Range: -5.9177

Max Act: 4.7936. Min Act: -0.0000

Data Index: 1876823 (The Pile)

Max Activating Token Index: 705

Text #11

Max Range: 5.9177. Min Range: -5.9177

Max Act: 4.2416. Min Act: -0.0000

Data Index: 220455 (The Pile)

Max Activating Token Index: 56

Text #12

Max Range: 5.9177. Min Range: -5.9177

Max Act: 4.3998. Min Act: -0.0000

Data Index: 561313 (The Pile)

Max Activating Token Index: 593

Text #13

Max Range: 5.9177. Min Range: -5.9177

Max Act: 4.7136. Min Act: -0.0000

Data Index: 1635431 (The Pile)

Max Activating Token Index: 372

Text #14

Max Range: 5.9177. Min Range: -5.9177

Max Act: 4.1691. Min Act: -0.0000

Data Index: 1093518 (The Pile)

Max Activating Token Index: 252

Text #15

Max Range: 5.9177. Min Range: -5.9177

Max Act: 4.3525. Min Act: -0.0000

Data Index: 486516 (The Pile)

Max Activating Token Index: 874

Text #16

Max Range: 5.9177. Min Range: -5.9177

Max Act: 4.3034. Min Act: -0.0000

Data Index: 1026872 (The Pile)

Max Activating Token Index: 596

Text #17

Max Range: 5.9177. Min Range: -5.9177

Max Act: 4.2476. Min Act: -0.0000

Data Index: 1822563 (The Pile)

Max Activating Token Index: 555

Text #18

Max Range: 5.9177. Min Range: -5.9177

Max Act: 4.2216. Min Act: -0.0000

Data Index: 1273392 (The Pile)

Max Activating Token Index: 391

Text #19

Max Range: 5.9177. Min Range: -5.9177

Max Act: 4.0481. Min Act: -0.0000

Data Index: 959021 (The Pile)

Max Activating Token Index: 603