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

Dataset: The Pile

Neuron 1795 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.8784. Min Act: -0.0000

Data Index: 1373402 (The Pile)

Max Activating Token Index: 341

Text #1

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.6415. Min Act: -0.0000

Data Index: 114316 (The Pile)

Max Activating Token Index: 577

Text #2

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.5927. Min Act: 0.0000

Data Index: 1710981 (The Pile)

Max Activating Token Index: 150

Text #3

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.4887. Min Act: -0.0000

Data Index: 1337116 (The Pile)

Max Activating Token Index: 354

Text #4

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.3923. Min Act: -0.0000

Data Index: 332772 (The Pile)

Max Activating Token Index: 143

Text #5

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.4601. Min Act: -0.0000

Data Index: 1632074 (The Pile)

Max Activating Token Index: 179

Text #6

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.3828. Min Act: -0.0000

Data Index: 1439122 (The Pile)

Max Activating Token Index: 1022

Text #7

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.4321. Min Act: -0.0000

Data Index: 1601331 (The Pile)

Max Activating Token Index: 555

Text #8

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.2568. Min Act: -0.0000

Data Index: 86036 (The Pile)

Max Activating Token Index: 899

Text #9

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.3468. Min Act: -0.0000

Data Index: 1541013 (The Pile)

Max Activating Token Index: 943

Text #10

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.2417. Min Act: -0.0000

Data Index: 197214 (The Pile)

Max Activating Token Index: 168

Text #11

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.1733. Min Act: -0.0000

Data Index: 522668 (The Pile)

Max Activating Token Index: 375

Text #12

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.1905. Min Act: -0.0000

Data Index: 12502 (The Pile)

Max Activating Token Index: 488

Text #13

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.1851. Min Act: -0.0000

Data Index: 1526460 (The Pile)

Max Activating Token Index: 482

Text #14

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.1430. Min Act: -0.0000

Data Index: 211693 (The Pile)

Max Activating Token Index: 1014

Text #15

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.1453. Min Act: 0.0000

Data Index: 926200 (The Pile)

Max Activating Token Index: 427

Text #16

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.1063. Min Act: 0.0000

Data Index: 397844 (The Pile)

Max Activating Token Index: 203

Text #17

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.0568. Min Act: -0.0000

Data Index: 516570 (The Pile)

Max Activating Token Index: 451

Text #18

Max Range: 1.8784. Min Range: -1.8784

Max Act: 0.9972. Min Act: -0.0000

Data Index: 1100241 (The Pile)

Max Activating Token Index: 250

Text #19

Max Range: 1.8784. Min Range: -1.8784

Max Act: 0.9044. Min Act: -0.0000

Data Index: 1055122 (The Pile)

Max Activating Token Index: 719