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

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

Neuron 878 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3365. Min Range: -2.3365

Max Act: 2.3297. Min Act: -0.0000

Data Index: 630366 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 2.3365. Min Range: -2.3365

Max Act: 2.3365. Min Act: -0.0000

Data Index: 406907 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 2.3365. Min Range: -2.3365

Max Act: 2.0298. Min Act: -0.0000

Data Index: 758433 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 2.3365. Min Range: -2.3365

Max Act: 1.8639. Min Act: -0.0000

Data Index: 876016 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 2.3365. Min Range: -2.3365

Max Act: 1.9559. Min Act: -0.0000

Data Index: 124412 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 2.3365. Min Range: -2.3365

Max Act: 2.0174. Min Act: -0.0000

Data Index: 1207129 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 2.3365. Min Range: -2.3365

Max Act: 1.9056. Min Act: -0.0000

Data Index: 1586577 (Python Code)

Max Activating Token Index: 792

Text #7

Max Range: 2.3365. Min Range: -2.3365

Max Act: 1.8498. Min Act: -0.0000

Data Index: 1362313 (Python Code)

Max Activating Token Index: 613

Text #8

Max Range: 2.3365. Min Range: -2.3365

Max Act: 1.9430. Min Act: -0.0000

Data Index: 911857 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 2.3365. Min Range: -2.3365

Max Act: 1.8095. Min Act: -0.0000

Data Index: 738155 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 2.3365. Min Range: -2.3365

Max Act: 1.7463. Min Act: -0.0000

Data Index: 1046136 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 2.3365. Min Range: -2.3365

Max Act: 1.7477. Min Act: -0.0000

Data Index: 726590 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 2.3365. Min Range: -2.3365

Max Act: 1.6908. Min Act: -0.0000

Data Index: 907828 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 2.3365. Min Range: -2.3365

Max Act: 1.7842. Min Act: -0.0000

Data Index: 318195 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 2.3365. Min Range: -2.3365

Max Act: 1.5880. Min Act: -0.0000

Data Index: 620262 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 2.3365. Min Range: -2.3365

Max Act: 1.7759. Min Act: -0.0000

Data Index: 350717 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 2.3365. Min Range: -2.3365

Max Act: 1.6082. Min Act: -0.0000

Data Index: 340388 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 2.3365. Min Range: -2.3365

Max Act: 1.4765. Min Act: -0.0000

Data Index: 470646 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 2.3365. Min Range: -2.3365

Max Act: 1.5606. Min Act: -0.0000

Data Index: 1246156 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 2.3365. Min Range: -2.3365

Max Act: 1.5514. Min Act: -0.0000

Data Index: 1285842 (C4 (Web Text))

Max Activating Token Index: 28