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

Dataset: The Pile

Neuron 3175 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.3432. Min Act: -0.0000

Data Index: 138280 (The Pile)

Max Activating Token Index: 157

Text #1

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.2585. Min Act: -0.0000

Data Index: 1584382 (The Pile)

Max Activating Token Index: 158

Text #2

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.9833. Min Act: -0.0000

Data Index: 1893338 (The Pile)

Max Activating Token Index: 475

Text #3

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.9703. Min Act: -0.0000

Data Index: 1917200 (The Pile)

Max Activating Token Index: 932

Text #4

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.9230. Min Act: -0.0000

Data Index: 1122894 (The Pile)

Max Activating Token Index: 44

Text #5

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.8738. Min Act: -0.0000

Data Index: 713670 (The Pile)

Max Activating Token Index: 228

Text #6

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.8667. Min Act: -0.0000

Data Index: 1862954 (The Pile)

Max Activating Token Index: 129

Text #7

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.8123. Min Act: -0.0000

Data Index: 925378 (The Pile)

Max Activating Token Index: 516

Text #8

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.8072. Min Act: -0.0000

Data Index: 1815100 (The Pile)

Max Activating Token Index: 947

Text #9

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.7817. Min Act: -0.0000

Data Index: 1401270 (The Pile)

Max Activating Token Index: 166

Text #10

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.7780. Min Act: -0.0000

Data Index: 1327210 (The Pile)

Max Activating Token Index: 62

Text #11

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.7803. Min Act: -0.0000

Data Index: 1368261 (The Pile)

Max Activating Token Index: 91

Text #12

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.8407. Min Act: -0.0000

Data Index: 1059582 (The Pile)

Max Activating Token Index: 217

Text #13

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.7819. Min Act: -0.0000

Data Index: 1420434 (The Pile)

Max Activating Token Index: 110

Text #14

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.7459. Min Act: -0.0000

Data Index: 569028 (The Pile)

Max Activating Token Index: 252

Text #15

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.6840. Min Act: -0.0000

Data Index: 1765172 (The Pile)

Max Activating Token Index: 944

Text #16

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.6981. Min Act: -0.0000

Data Index: 1545590 (The Pile)

Max Activating Token Index: 588

Text #17

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.6788. Min Act: -0.0000

Data Index: 1355692 (The Pile)

Max Activating Token Index: 454

Text #18

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.6916. Min Act: -0.0000

Data Index: 423312 (The Pile)

Max Activating Token Index: 184

Text #19

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.7063. Min Act: -0.0000

Data Index: 391998 (The Pile)

Max Activating Token Index: 780