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

Dataset: The Pile

Neuron 4477 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2340. Min Range: -1.2340

Max Act: 1.2340. Min Act: -0.0000

Data Index: 103461 (The Pile)

Max Activating Token Index: 655

Text #1

Max Range: 1.2340. Min Range: -1.2340

Max Act: 1.0968. Min Act: -0.0000

Data Index: 718073 (The Pile)

Max Activating Token Index: 678

Text #2

Max Range: 1.2340. Min Range: -1.2340

Max Act: 1.0052. Min Act: -0.0000

Data Index: 139767 (The Pile)

Max Activating Token Index: 92

Text #3

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.9359. Min Act: -0.0000

Data Index: 652311 (The Pile)

Max Activating Token Index: 787

Text #4

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.9759. Min Act: -0.0000

Data Index: 1061710 (The Pile)

Max Activating Token Index: 86

Text #5

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.9345. Min Act: -0.0000

Data Index: 672959 (The Pile)

Max Activating Token Index: 887

Text #6

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.9972. Min Act: -0.0000

Data Index: 480334 (The Pile)

Max Activating Token Index: 796

Text #7

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.8533. Min Act: -0.0000

Data Index: 1585896 (The Pile)

Max Activating Token Index: 975

Text #8

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.9567. Min Act: -0.0000

Data Index: 1031827 (The Pile)

Max Activating Token Index: 191

Text #9

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.9904. Min Act: -0.0000

Data Index: 1577850 (The Pile)

Max Activating Token Index: 291

Text #10

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.9531. Min Act: -0.0000

Data Index: 744403 (The Pile)

Max Activating Token Index: 993

Text #11

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.9215. Min Act: -0.0000

Data Index: 129531 (The Pile)

Max Activating Token Index: 311

Text #12

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.9458. Min Act: -0.0000

Data Index: 711684 (The Pile)

Max Activating Token Index: 810

Text #13

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.8760. Min Act: -0.0000

Data Index: 1988451 (The Pile)

Max Activating Token Index: 40

Text #14

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.8898. Min Act: -0.0000

Data Index: 229987 (The Pile)

Max Activating Token Index: 296

Text #15

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.8849. Min Act: -0.0000

Data Index: 1024341 (The Pile)

Max Activating Token Index: 726

Text #16

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.9269. Min Act: -0.0000

Data Index: 780074 (The Pile)

Max Activating Token Index: 939

Text #17

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.8864. Min Act: -0.0000

Data Index: 1996036 (The Pile)

Max Activating Token Index: 873

Text #18

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.7321. Min Act: -0.0000

Data Index: 1252021 (The Pile)

Max Activating Token Index: 774

Text #19

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.8338. Min Act: -0.0000

Data Index: 169536 (The Pile)

Max Activating Token Index: 526