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

Dataset: The Pile

Neuron 165 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1399. Min Act: -0.0000

Data Index: 1848568 (The Pile)

Max Activating Token Index: 359

Text #1

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1093. Min Act: -0.0000

Data Index: 616335 (The Pile)

Max Activating Token Index: 1006

Text #2

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1018. Min Act: -0.0000

Data Index: 56111 (The Pile)

Max Activating Token Index: 292

Text #3

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0968. Min Act: -0.0000

Data Index: 743916 (The Pile)

Max Activating Token Index: 113

Text #4

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0900. Min Act: -0.0000

Data Index: 1795192 (The Pile)

Max Activating Token Index: 686

Text #5

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0900. Min Act: -0.0000

Data Index: 979488 (The Pile)

Max Activating Token Index: 163

Text #6

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0932. Min Act: -0.0000

Data Index: 1676266 (The Pile)

Max Activating Token Index: 981

Text #7

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0904. Min Act: -0.0000

Data Index: 39815 (The Pile)

Max Activating Token Index: 214

Text #8

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0896. Min Act: -0.0000

Data Index: 1447780 (The Pile)

Max Activating Token Index: 33

Text #9

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0964. Min Act: -0.0000

Data Index: 1142708 (The Pile)

Max Activating Token Index: 251

Text #10

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0893. Min Act: -0.0000

Data Index: 919796 (The Pile)

Max Activating Token Index: 329

Text #11

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0957. Min Act: -0.0000

Data Index: 1888330 (The Pile)

Max Activating Token Index: 852

Text #12

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0890. Min Act: -0.0000

Data Index: 1188271 (The Pile)

Max Activating Token Index: 751

Text #13

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0862. Min Act: -0.0000

Data Index: 1618775 (The Pile)

Max Activating Token Index: 63

Text #14

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0951. Min Act: -0.0000

Data Index: 1011329 (The Pile)

Max Activating Token Index: 528

Text #15

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0948. Min Act: 0.0000

Data Index: 1867148 (The Pile)

Max Activating Token Index: 103

Text #16

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0926. Min Act: -0.0000

Data Index: 1347966 (The Pile)

Max Activating Token Index: 336

Text #17

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0893. Min Act: -0.0000

Data Index: 1059532 (The Pile)

Max Activating Token Index: 302

Text #18

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0878. Min Act: -0.0000

Data Index: 1767863 (The Pile)

Max Activating Token Index: 671

Text #19

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0875. Min Act: -0.0000

Data Index: 1987904 (The Pile)

Max Activating Token Index: 472