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

Dataset: The Pile

Neuron 1204 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0587. Min Range: -1.0587

Max Act: 1.0473. Min Act: -0.0000

Data Index: 1876775 (The Pile)

Max Activating Token Index: 716

Text #1

Max Range: 1.0587. Min Range: -1.0587

Max Act: 1.0587. Min Act: -0.0000

Data Index: 948296 (The Pile)

Max Activating Token Index: 318

Text #2

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.8975. Min Act: -0.0000

Data Index: 737133 (The Pile)

Max Activating Token Index: 177

Text #3

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.9444. Min Act: -0.0000

Data Index: 1864250 (The Pile)

Max Activating Token Index: 508

Text #4

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.8472. Min Act: -0.0000

Data Index: 1928187 (The Pile)

Max Activating Token Index: 183

Text #5

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.8780. Min Act: -0.0000

Data Index: 546320 (The Pile)

Max Activating Token Index: 33

Text #6

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.7690. Min Act: -0.0000

Data Index: 563535 (The Pile)

Max Activating Token Index: 221

Text #7

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.8951. Min Act: -0.0000

Data Index: 197546 (The Pile)

Max Activating Token Index: 186

Text #8

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.7876. Min Act: -0.0000

Data Index: 1023490 (The Pile)

Max Activating Token Index: 63

Text #9

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.7247. Min Act: -0.0000

Data Index: 193370 (The Pile)

Max Activating Token Index: 91

Text #10

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.9968. Min Act: -0.0000

Data Index: 830679 (The Pile)

Max Activating Token Index: 917

Text #11

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.8106. Min Act: -0.0000

Data Index: 1550837 (The Pile)

Max Activating Token Index: 169

Text #12

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.8128. Min Act: -0.0000

Data Index: 722448 (The Pile)

Max Activating Token Index: 814

Text #13

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.7940. Min Act: -0.0000

Data Index: 711991 (The Pile)

Max Activating Token Index: 690

Text #14

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.7544. Min Act: -0.0000

Data Index: 1018865 (The Pile)

Max Activating Token Index: 756

Text #15

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.6488. Min Act: -0.0000

Data Index: 312903 (The Pile)

Max Activating Token Index: 849

Text #16

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.6722. Min Act: -0.0000

Data Index: 1667224 (The Pile)

Max Activating Token Index: 352

Text #17

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.6767. Min Act: -0.0000

Data Index: 1302954 (The Pile)

Max Activating Token Index: 541

Text #18

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.7163. Min Act: -0.0000

Data Index: 1974716 (The Pile)

Max Activating Token Index: 687

Text #19

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.6724. Min Act: -0.0000

Data Index: 261120 (The Pile)

Max Activating Token Index: 523