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

Dataset: The Pile

Neuron 2304 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: 0.7835. Min Range: -0.7835

Max Act: 0.7835. Min Act: -0.0000

Data Index: 531373 (The Pile)

Max Activating Token Index: 938

Text #1

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.6956. Min Act: -0.0000

Data Index: 560179 (The Pile)

Max Activating Token Index: 878

Text #2

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.6660. Min Act: -0.0000

Data Index: 1083528 (The Pile)

Max Activating Token Index: 682

Text #3

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5984. Min Act: -0.0000

Data Index: 679924 (The Pile)

Max Activating Token Index: 835

Text #4

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5888. Min Act: -0.0000

Data Index: 541695 (The Pile)

Max Activating Token Index: 833

Text #5

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5711. Min Act: -0.0000

Data Index: 1023636 (The Pile)

Max Activating Token Index: 544

Text #6

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5675. Min Act: -0.0000

Data Index: 958084 (The Pile)

Max Activating Token Index: 999

Text #7

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5682. Min Act: -0.0000

Data Index: 938963 (The Pile)

Max Activating Token Index: 749

Text #8

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5853. Min Act: -0.0000

Data Index: 575297 (The Pile)

Max Activating Token Index: 537

Text #9

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.4937. Min Act: -0.0000

Data Index: 1557836 (The Pile)

Max Activating Token Index: 772

Text #10

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.4859. Min Act: -0.0000

Data Index: 1313207 (The Pile)

Max Activating Token Index: 435

Text #11

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.4911. Min Act: -0.0000

Data Index: 1772408 (The Pile)

Max Activating Token Index: 1011

Text #12

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.4833. Min Act: -0.0000

Data Index: 1131116 (The Pile)

Max Activating Token Index: 593

Text #13

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5073. Min Act: -0.0000

Data Index: 1524151 (The Pile)

Max Activating Token Index: 433

Text #14

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.4946. Min Act: -0.0000

Data Index: 1103971 (The Pile)

Max Activating Token Index: 637

Text #15

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.4890. Min Act: -0.0000

Data Index: 1047668 (The Pile)

Max Activating Token Index: 530

Text #16

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.4916. Min Act: -0.0000

Data Index: 1524224 (The Pile)

Max Activating Token Index: 380

Text #17

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5182. Min Act: -0.0000

Data Index: 1234302 (The Pile)

Max Activating Token Index: 622

Text #18

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.4927. Min Act: -0.0000

Data Index: 1399537 (The Pile)

Max Activating Token Index: 702

Text #19

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.4685. Min Act: -0.0000

Data Index: 1693180 (The Pile)

Max Activating Token Index: 941