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

Dataset: The Pile

Neuron 4979 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: 5.2829. Min Range: -5.2829

Max Act: 5.2829. Min Act: -0.0000

Data Index: 726777 (The Pile)

Max Activating Token Index: 186

Text #1

Max Range: 5.2829. Min Range: -5.2829

Max Act: 5.0754. Min Act: -0.0000

Data Index: 376110 (The Pile)

Max Activating Token Index: 8

Text #2

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.2335. Min Act: -0.0000

Data Index: 94122 (The Pile)

Max Activating Token Index: 811

Text #3

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.5330. Min Act: -0.0000

Data Index: 414380 (The Pile)

Max Activating Token Index: 10

Text #4

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.2985. Min Act: -0.0000

Data Index: 1484654 (The Pile)

Max Activating Token Index: 10

Text #5

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.2728. Min Act: -0.0000

Data Index: 116636 (The Pile)

Max Activating Token Index: 8

Text #6

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.0913. Min Act: -0.0000

Data Index: 705086 (The Pile)

Max Activating Token Index: 310

Text #7

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.2431. Min Act: -0.0000

Data Index: 142222 (The Pile)

Max Activating Token Index: 10

Text #8

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.0469. Min Act: -0.0000

Data Index: 114426 (The Pile)

Max Activating Token Index: 10

Text #9

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.3733. Min Act: -0.0000

Data Index: 384233 (The Pile)

Max Activating Token Index: 32

Text #10

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.3897. Min Act: -0.0000

Data Index: 155216 (The Pile)

Max Activating Token Index: 666

Text #11

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.1947. Min Act: -0.0000

Data Index: 1510220 (The Pile)

Max Activating Token Index: 10

Text #12

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.1725. Min Act: -0.0000

Data Index: 1732738 (The Pile)

Max Activating Token Index: 135

Text #13

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.3056. Min Act: -0.0000

Data Index: 1787923 (The Pile)

Max Activating Token Index: 23

Text #14

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.3039. Min Act: -0.0000

Data Index: 797123 (The Pile)

Max Activating Token Index: 8

Text #15

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.1091. Min Act: -0.0000

Data Index: 712844 (The Pile)

Max Activating Token Index: 55

Text #16

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.2387. Min Act: -0.0000

Data Index: 22860 (The Pile)

Max Activating Token Index: 12

Text #17

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.0416. Min Act: -0.0000

Data Index: 1142941 (The Pile)

Max Activating Token Index: 11

Text #18

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.1815. Min Act: -0.0000

Data Index: 501949 (The Pile)

Max Activating Token Index: 102

Text #19

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.0035. Min Act: -0.0000

Data Index: 1021455 (The Pile)

Max Activating Token Index: 9