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

Dataset: The Pile

Neuron 3109 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0241. Min Range: -1.0241

Max Act: 1.0241. Min Act: -0.0000

Data Index: 1536476 (The Pile)

Max Activating Token Index: 110

Text #1

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.7770. Min Act: -0.0000

Data Index: 1255479 (The Pile)

Max Activating Token Index: 345

Text #2

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.8658. Min Act: -0.0000

Data Index: 537139 (The Pile)

Max Activating Token Index: 930

Text #3

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.8077. Min Act: -0.0000

Data Index: 852753 (The Pile)

Max Activating Token Index: 10

Text #4

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.7465. Min Act: -0.0000

Data Index: 765885 (The Pile)

Max Activating Token Index: 12

Text #5

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.8374. Min Act: -0.0000

Data Index: 827944 (The Pile)

Max Activating Token Index: 499

Text #6

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.7599. Min Act: -0.0000

Data Index: 177716 (The Pile)

Max Activating Token Index: 775

Text #7

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.7883. Min Act: -0.0000

Data Index: 1081024 (The Pile)

Max Activating Token Index: 233

Text #8

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.7689. Min Act: -0.0000

Data Index: 1677263 (The Pile)

Max Activating Token Index: 426

Text #9

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.7221. Min Act: -0.0000

Data Index: 1209027 (The Pile)

Max Activating Token Index: 387

Text #10

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.6926. Min Act: -0.0000

Data Index: 1757434 (The Pile)

Max Activating Token Index: 232

Text #11

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.7366. Min Act: -0.0000

Data Index: 981339 (The Pile)

Max Activating Token Index: 303

Text #12

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.7350. Min Act: -0.0000

Data Index: 1927129 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.6783. Min Act: -0.0000

Data Index: 1930191 (The Pile)

Max Activating Token Index: 901

Text #14

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.7612. Min Act: -0.0000

Data Index: 1985524 (The Pile)

Max Activating Token Index: 160

Text #15

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.7136. Min Act: -0.0000

Data Index: 61658 (The Pile)

Max Activating Token Index: 536

Text #16

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.7045. Min Act: -0.0000

Data Index: 1729639 (The Pile)

Max Activating Token Index: 762

Text #17

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.6602. Min Act: -0.0000

Data Index: 909540 (The Pile)

Max Activating Token Index: 288

Text #18

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.7553. Min Act: -0.0000

Data Index: 1967702 (The Pile)

Max Activating Token Index: 859

Text #19

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.6991. Min Act: -0.0000

Data Index: 1956075 (The Pile)

Max Activating Token Index: 363