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

Dataset: The Pile

Neuron 462 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.8915. Min Act: -0.0000

Data Index: 1604486 (The Pile)

Max Activating Token Index: 795

Text #1

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.8672. Min Act: -0.0000

Data Index: 714775 (The Pile)

Max Activating Token Index: 118

Text #2

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.7974. Min Act: -0.0000

Data Index: 881193 (The Pile)

Max Activating Token Index: 209

Text #3

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.8174. Min Act: -0.0000

Data Index: 451213 (The Pile)

Max Activating Token Index: 541

Text #4

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.8123. Min Act: -0.0000

Data Index: 1003250 (The Pile)

Max Activating Token Index: 479

Text #5

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.8363. Min Act: -0.0000

Data Index: 1217302 (The Pile)

Max Activating Token Index: 480

Text #6

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.7662. Min Act: -0.0000

Data Index: 960821 (The Pile)

Max Activating Token Index: 770

Text #7

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.7518. Min Act: -0.0000

Data Index: 1948344 (The Pile)

Max Activating Token Index: 38

Text #8

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.7542. Min Act: -0.0000

Data Index: 318689 (The Pile)

Max Activating Token Index: 165

Text #9

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.7251. Min Act: -0.0000

Data Index: 1135437 (The Pile)

Max Activating Token Index: 38

Text #10

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.8052. Min Act: -0.0000

Data Index: 1244444 (The Pile)

Max Activating Token Index: 220

Text #11

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.6980. Min Act: -0.0000

Data Index: 1396180 (The Pile)

Max Activating Token Index: 611

Text #12

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.6369. Min Act: -0.0000

Data Index: 588999 (The Pile)

Max Activating Token Index: 733

Text #13

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.7350. Min Act: -0.0000

Data Index: 1312207 (The Pile)

Max Activating Token Index: 360

Text #14

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.7295. Min Act: -0.0000

Data Index: 1071332 (The Pile)

Max Activating Token Index: 38

Text #15

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.7221. Min Act: -0.0000

Data Index: 1646887 (The Pile)

Max Activating Token Index: 84

Text #16

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.6936. Min Act: -0.0000

Data Index: 1354662 (The Pile)

Max Activating Token Index: 92

Text #17

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.6885. Min Act: -0.0000

Data Index: 189853 (The Pile)

Max Activating Token Index: 113

Text #18

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.6714. Min Act: -0.0000

Data Index: 1233030 (The Pile)

Max Activating Token Index: 627

Text #19

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.6695. Min Act: -0.0000

Data Index: 999033 (The Pile)

Max Activating Token Index: 540