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

Dataset: The Pile

Neuron 3482 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: 0.3448. Min Range: -0.3448

Max Act: 0.3448. Min Act: -0.0000

Data Index: 802875 (The Pile)

Max Activating Token Index: 256

Text #1

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.3423. Min Act: -0.0000

Data Index: 1874213 (The Pile)

Max Activating Token Index: 100

Text #2

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.3292. Min Act: -0.0000

Data Index: 1825516 (The Pile)

Max Activating Token Index: 40

Text #3

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.3064. Min Act: -0.0000

Data Index: 1892467 (The Pile)

Max Activating Token Index: 587

Text #4

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.3016. Min Act: -0.0000

Data Index: 1742848 (The Pile)

Max Activating Token Index: 216

Text #5

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.3014. Min Act: -0.0000

Data Index: 660357 (The Pile)

Max Activating Token Index: 473

Text #6

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2792. Min Act: -0.0000

Data Index: 1502622 (The Pile)

Max Activating Token Index: 160

Text #7

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2875. Min Act: -0.0000

Data Index: 1974055 (The Pile)

Max Activating Token Index: 957

Text #8

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2909. Min Act: -0.0000

Data Index: 722579 (The Pile)

Max Activating Token Index: 359

Text #9

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2978. Min Act: -0.0000

Data Index: 1235723 (The Pile)

Max Activating Token Index: 275

Text #10

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2984. Min Act: -0.0000

Data Index: 1570764 (The Pile)

Max Activating Token Index: 953

Text #11

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2866. Min Act: -0.0000

Data Index: 1240289 (The Pile)

Max Activating Token Index: 953

Text #12

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2707. Min Act: -0.0000

Data Index: 637368 (The Pile)

Max Activating Token Index: 1011

Text #13

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2648. Min Act: -0.0000

Data Index: 516812 (The Pile)

Max Activating Token Index: 1021

Text #14

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2785. Min Act: -0.0000

Data Index: 1054922 (The Pile)

Max Activating Token Index: 374

Text #15

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2862. Min Act: -0.0000

Data Index: 1526631 (The Pile)

Max Activating Token Index: 344

Text #16

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2631. Min Act: -0.0000

Data Index: 1982706 (The Pile)

Max Activating Token Index: 225

Text #17

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2723. Min Act: -0.0000

Data Index: 131883 (The Pile)

Max Activating Token Index: 283

Text #18

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2631. Min Act: -0.0000

Data Index: 1388909 (The Pile)

Max Activating Token Index: 97

Text #19

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2994. Min Act: -0.0000

Data Index: 492098 (The Pile)

Max Activating Token Index: 231