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

Dataset: The Pile

Neuron 3692 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: 0.1414. Min Range: -0.1414

Max Act: 0.1414. Min Act: -0.0000

Data Index: 1588140 (The Pile)

Max Activating Token Index: 874

Text #1

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1367. Min Act: -0.0000

Data Index: 1818464 (The Pile)

Max Activating Token Index: 625

Text #2

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1151. Min Act: -0.0000

Data Index: 220933 (The Pile)

Max Activating Token Index: 853

Text #3

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1200. Min Act: -0.0000

Data Index: 1645017 (The Pile)

Max Activating Token Index: 165

Text #4

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1085. Min Act: 0.0000

Data Index: 976450 (The Pile)

Max Activating Token Index: 827

Text #5

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1034. Min Act: -0.0000

Data Index: 227868 (The Pile)

Max Activating Token Index: 337

Text #6

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1026. Min Act: 0.0000

Data Index: 604842 (The Pile)

Max Activating Token Index: 218

Text #7

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0984. Min Act: -0.0000

Data Index: 1541757 (The Pile)

Max Activating Token Index: 773

Text #8

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1004. Min Act: -0.0000

Data Index: 987120 (The Pile)

Max Activating Token Index: 42

Text #9

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0924. Min Act: -0.0000

Data Index: 1903424 (The Pile)

Max Activating Token Index: 426

Text #10

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0951. Min Act: -0.0000

Data Index: 892635 (The Pile)

Max Activating Token Index: 416

Text #11

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0946. Min Act: -0.0000

Data Index: 1798178 (The Pile)

Max Activating Token Index: 860

Text #12

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0868. Min Act: -0.0000

Data Index: 1655975 (The Pile)

Max Activating Token Index: 135

Text #13

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0964. Min Act: -0.0000

Data Index: 1170096 (The Pile)

Max Activating Token Index: 184

Text #14

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0936. Min Act: -0.0000

Data Index: 1319710 (The Pile)

Max Activating Token Index: 725

Text #15

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0922. Min Act: -0.0000

Data Index: 481828 (The Pile)

Max Activating Token Index: 173

Text #16

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0887. Min Act: -0.0000

Data Index: 1539284 (The Pile)

Max Activating Token Index: 116

Text #17

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0840. Min Act: 0.0000

Data Index: 264401 (The Pile)

Max Activating Token Index: 558

Text #18

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0903. Min Act: -0.0000

Data Index: 488616 (The Pile)

Max Activating Token Index: 797

Text #19

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0963. Min Act: -0.0000

Data Index: 1208264 (The Pile)

Max Activating Token Index: 401