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

Dataset: The Pile

Neuron 218 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.8787. Min Act: -0.0000

Data Index: 1948996 (The Pile)

Max Activating Token Index: 511

Text #1

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.7671. Min Act: -0.0000

Data Index: 1157323 (The Pile)

Max Activating Token Index: 256

Text #2

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.8088. Min Act: -0.0000

Data Index: 1806425 (The Pile)

Max Activating Token Index: 663

Text #3

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.7518. Min Act: -0.0000

Data Index: 758772 (The Pile)

Max Activating Token Index: 53

Text #4

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.7419. Min Act: -0.0000

Data Index: 1378976 (The Pile)

Max Activating Token Index: 441

Text #5

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.7207. Min Act: -0.0000

Data Index: 1512073 (The Pile)

Max Activating Token Index: 439

Text #6

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.6713. Min Act: -0.0000

Data Index: 1714911 (The Pile)

Max Activating Token Index: 154

Text #7

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.5766. Min Act: -0.0000

Data Index: 1412983 (The Pile)

Max Activating Token Index: 626

Text #8

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.6288. Min Act: -0.0000

Data Index: 648944 (The Pile)

Max Activating Token Index: 885

Text #9

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.6892. Min Act: -0.0000

Data Index: 238287 (The Pile)

Max Activating Token Index: 103

Text #10

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.6708. Min Act: -0.0000

Data Index: 785299 (The Pile)

Max Activating Token Index: 136

Text #11

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.6565. Min Act: -0.0000

Data Index: 911461 (The Pile)

Max Activating Token Index: 98

Text #12

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.6480. Min Act: -0.0000

Data Index: 1236288 (The Pile)

Max Activating Token Index: 429

Text #13

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.6720. Min Act: -0.0000

Data Index: 398779 (The Pile)

Max Activating Token Index: 911

Text #14

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.6654. Min Act: -0.0000

Data Index: 213170 (The Pile)

Max Activating Token Index: 137

Text #15

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.6201. Min Act: -0.0000

Data Index: 1386663 (The Pile)

Max Activating Token Index: 156

Text #16

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.6011. Min Act: -0.0000

Data Index: 1333506 (The Pile)

Max Activating Token Index: 248

Text #17

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.6256. Min Act: -0.0000

Data Index: 768131 (The Pile)

Max Activating Token Index: 584

Text #18

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.5950. Min Act: -0.0000

Data Index: 1543847 (The Pile)

Max Activating Token Index: 93

Text #19

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.5783. Min Act: -0.0000

Data Index: 1307372 (The Pile)

Max Activating Token Index: 633