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

Dataset: The Pile

Neuron 129 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.6138. Min Act: -0.0000

Data Index: 1636210 (The Pile)

Max Activating Token Index: 643

Text #1

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4567. Min Act: -0.0000

Data Index: 1052722 (The Pile)

Max Activating Token Index: 45

Text #2

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4673. Min Act: -0.0000

Data Index: 1733439 (The Pile)

Max Activating Token Index: 31

Text #3

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4620. Min Act: -0.0000

Data Index: 1134062 (The Pile)

Max Activating Token Index: 794

Text #4

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4244. Min Act: -0.0000

Data Index: 1369654 (The Pile)

Max Activating Token Index: 947

Text #5

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3745. Min Act: -0.0000

Data Index: 1308731 (The Pile)

Max Activating Token Index: 630

Text #6

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3358. Min Act: -0.0000

Data Index: 945871 (The Pile)

Max Activating Token Index: 1022

Text #7

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3465. Min Act: -0.0000

Data Index: 1499842 (The Pile)

Max Activating Token Index: 189

Text #8

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3593. Min Act: -0.0000

Data Index: 1336643 (The Pile)

Max Activating Token Index: 472

Text #9

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3342. Min Act: -0.0000

Data Index: 745684 (The Pile)

Max Activating Token Index: 730

Text #10

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3514. Min Act: -0.0000

Data Index: 455413 (The Pile)

Max Activating Token Index: 860

Text #11

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3486. Min Act: -0.0000

Data Index: 622697 (The Pile)

Max Activating Token Index: 967

Text #12

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3956. Min Act: -0.0000

Data Index: 98584 (The Pile)

Max Activating Token Index: 226

Text #13

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3100. Min Act: -0.0000

Data Index: 954143 (The Pile)

Max Activating Token Index: 332

Text #14

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3179. Min Act: -0.0000

Data Index: 831849 (The Pile)

Max Activating Token Index: 22

Text #15

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3594. Min Act: -0.0000

Data Index: 1411434 (The Pile)

Max Activating Token Index: 196

Text #16

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3457. Min Act: -0.0000

Data Index: 526889 (The Pile)

Max Activating Token Index: 175

Text #17

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3103. Min Act: -0.0000

Data Index: 1324010 (The Pile)

Max Activating Token Index: 384

Text #18

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.2796. Min Act: -0.0000

Data Index: 1968015 (The Pile)

Max Activating Token Index: 745

Text #19

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3437. Min Act: -0.0000

Data Index: 1549582 (The Pile)

Max Activating Token Index: 919