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

Dataset: The Pile

Neuron 1662 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: 1.8072. Min Range: -1.8072

Max Act: 1.8072. Min Act: -0.0000

Data Index: 142183 (The Pile)

Max Activating Token Index: 33

Text #1

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.4390. Min Act: -0.0000

Data Index: 1326337 (The Pile)

Max Activating Token Index: 88

Text #2

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.4436. Min Act: -0.0000

Data Index: 1031436 (The Pile)

Max Activating Token Index: 971

Text #3

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.4032. Min Act: -0.0000

Data Index: 1547774 (The Pile)

Max Activating Token Index: 17

Text #4

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.3851. Min Act: -0.0000

Data Index: 1757322 (The Pile)

Max Activating Token Index: 243

Text #5

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.1973. Min Act: -0.0000

Data Index: 1731999 (The Pile)

Max Activating Token Index: 54

Text #6

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.3753. Min Act: -0.0000

Data Index: 1717184 (The Pile)

Max Activating Token Index: 36

Text #7

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.1907. Min Act: -0.0000

Data Index: 385036 (The Pile)

Max Activating Token Index: 90

Text #8

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.2092. Min Act: -0.0000

Data Index: 843531 (The Pile)

Max Activating Token Index: 155

Text #9

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.2195. Min Act: -0.0000

Data Index: 357097 (The Pile)

Max Activating Token Index: 549

Text #10

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.2897. Min Act: -0.0000

Data Index: 1170611 (The Pile)

Max Activating Token Index: 38

Text #11

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.1986. Min Act: -0.0000

Data Index: 1706093 (The Pile)

Max Activating Token Index: 546

Text #12

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.1593. Min Act: -0.0000

Data Index: 1868005 (The Pile)

Max Activating Token Index: 319

Text #13

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.1478. Min Act: -0.0000

Data Index: 1492029 (The Pile)

Max Activating Token Index: 300

Text #14

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.1689. Min Act: -0.0000

Data Index: 67197 (The Pile)

Max Activating Token Index: 67

Text #15

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.1121. Min Act: -0.0000

Data Index: 585900 (The Pile)

Max Activating Token Index: 176

Text #16

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.0857. Min Act: -0.0000

Data Index: 1382780 (The Pile)

Max Activating Token Index: 275

Text #17

Max Range: 1.8072. Min Range: -1.8072

Max Act: 0.9894. Min Act: -0.0000

Data Index: 1223727 (The Pile)

Max Activating Token Index: 66

Text #18

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.0384. Min Act: -0.0000

Data Index: 1216044 (The Pile)

Max Activating Token Index: 787

Text #19

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.0873. Min Act: -0.0000

Data Index: 1517518 (The Pile)

Max Activating Token Index: 801