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

Dataset: The Pile

Neuron 2549 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.7981. Min Act: -0.0000

Data Index: 232273 (The Pile)

Max Activating Token Index: 754

Text #1

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.4212. Min Act: -0.0000

Data Index: 1634155 (The Pile)

Max Activating Token Index: 786

Text #2

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.4267. Min Act: -0.0000

Data Index: 774389 (The Pile)

Max Activating Token Index: 382

Text #3

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.3444. Min Act: -0.0000

Data Index: 1095297 (The Pile)

Max Activating Token Index: 905

Text #4

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.4089. Min Act: -0.0000

Data Index: 1101826 (The Pile)

Max Activating Token Index: 471

Text #5

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.3068. Min Act: -0.0000

Data Index: 1471419 (The Pile)

Max Activating Token Index: 157

Text #6

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.3165. Min Act: -0.0000

Data Index: 1429234 (The Pile)

Max Activating Token Index: 723

Text #7

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.3046. Min Act: -0.0000

Data Index: 877512 (The Pile)

Max Activating Token Index: 103

Text #8

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.2368. Min Act: -0.0000

Data Index: 1808546 (The Pile)

Max Activating Token Index: 955

Text #9

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.3644. Min Act: -0.0000

Data Index: 1647612 (The Pile)

Max Activating Token Index: 722

Text #10

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.2068. Min Act: -0.0000

Data Index: 1564728 (The Pile)

Max Activating Token Index: 251

Text #11

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.2694. Min Act: -0.0000

Data Index: 1530416 (The Pile)

Max Activating Token Index: 194

Text #12

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.2669. Min Act: -0.0000

Data Index: 318342 (The Pile)

Max Activating Token Index: 50

Text #13

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.2396. Min Act: -0.0000

Data Index: 582547 (The Pile)

Max Activating Token Index: 180

Text #14

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.2385. Min Act: -0.0000

Data Index: 431371 (The Pile)

Max Activating Token Index: 821

Text #15

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.1566. Min Act: -0.0000

Data Index: 113115 (The Pile)

Max Activating Token Index: 458

Text #16

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.2302. Min Act: -0.0000

Data Index: 1400330 (The Pile)

Max Activating Token Index: 748

Text #17

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.2914. Min Act: -0.0000

Data Index: 1666858 (The Pile)

Max Activating Token Index: 180

Text #18

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.2133. Min Act: -0.0000

Data Index: 1862274 (The Pile)

Max Activating Token Index: 875

Text #19

Max Range: 1.7981. Min Range: -1.7981

Max Act: 1.1466. Min Act: -0.0000

Data Index: 954219 (The Pile)

Max Activating Token Index: 662