Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4082 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.7528. Min Act: -0.0000

Data Index: 256951 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.6782. Min Act: -0.0000

Data Index: 395125 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.6131. Min Act: -0.0000

Data Index: 160145 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.6119. Min Act: -0.0000

Data Index: 637976 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.5428. Min Act: 0.0000

Data Index: 199076 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4760. Min Act: -0.0000

Data Index: 610094 (C4 (Web Text))

Max Activating Token Index: 449

Text #6

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4868. Min Act: -0.0000

Data Index: 1220259 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4632. Min Act: -0.0000

Data Index: 302398 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4799. Min Act: -0.0000

Data Index: 244597 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4606. Min Act: -0.0000

Data Index: 1203336 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4551. Min Act: -0.0000

Data Index: 393021 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4825. Min Act: -0.0000

Data Index: 1186052 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4493. Min Act: -0.0000

Data Index: 152062 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4612. Min Act: -0.0000

Data Index: 255043 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4586. Min Act: -0.0000

Data Index: 171742 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4433. Min Act: -0.0000

Data Index: 111045 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4537. Min Act: -0.0000

Data Index: 873813 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4334. Min Act: -0.0000

Data Index: 779402 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4340. Min Act: -0.0000

Data Index: 1131615 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4499. Min Act: -0.0000

Data Index: 716136 (C4 (Web Text))

Max Activating Token Index: 596