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

Dataset: The Pile

Neuron 3762 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: 0.7818. Min Range: -0.7818

Max Act: 0.7522. Min Act: -0.0000

Data Index: 82548 (The Pile)

Max Activating Token Index: 100

Text #1

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.7818. Min Act: -0.0000

Data Index: 1047175 (The Pile)

Max Activating Token Index: 519

Text #2

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.7366. Min Act: -0.0000

Data Index: 683435 (The Pile)

Max Activating Token Index: 787

Text #3

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.7301. Min Act: -0.0000

Data Index: 1649182 (The Pile)

Max Activating Token Index: 115

Text #4

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.7101. Min Act: 0.0000

Data Index: 1648869 (The Pile)

Max Activating Token Index: 100

Text #5

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6838. Min Act: -0.0000

Data Index: 171665 (The Pile)

Max Activating Token Index: 868

Text #6

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6811. Min Act: -0.0000

Data Index: 527518 (The Pile)

Max Activating Token Index: 88

Text #7

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6881. Min Act: 0.0000

Data Index: 894961 (The Pile)

Max Activating Token Index: 230

Text #8

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6857. Min Act: -0.0000

Data Index: 827681 (The Pile)

Max Activating Token Index: 903

Text #9

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6958. Min Act: -0.0000

Data Index: 1811376 (The Pile)

Max Activating Token Index: 503

Text #10

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6707. Min Act: -0.0000

Data Index: 1485043 (The Pile)

Max Activating Token Index: 83

Text #11

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6834. Min Act: -0.0000

Data Index: 1005317 (The Pile)

Max Activating Token Index: 722

Text #12

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6277. Min Act: -0.0000

Data Index: 1960931 (The Pile)

Max Activating Token Index: 473

Text #13

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6899. Min Act: -0.0000

Data Index: 526437 (The Pile)

Max Activating Token Index: 532

Text #14

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6402. Min Act: -0.0000

Data Index: 1456871 (The Pile)

Max Activating Token Index: 984

Text #15

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6312. Min Act: -0.0000

Data Index: 1668218 (The Pile)

Max Activating Token Index: 730

Text #16

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6557. Min Act: -0.0000

Data Index: 582127 (The Pile)

Max Activating Token Index: 616

Text #17

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6483. Min Act: -0.0000

Data Index: 1076366 (The Pile)

Max Activating Token Index: 782

Text #18

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6348. Min Act: -0.0000

Data Index: 1055073 (The Pile)

Max Activating Token Index: 597

Text #19

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6643. Min Act: -0.0000

Data Index: 697650 (The Pile)

Max Activating Token Index: 933