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

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

Neuron 3275 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.9253. Min Act: -0.0000

Data Index: 250164 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.9588. Min Act: -0.0000

Data Index: 873499 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 1.0393. Min Range: -1.0393

Max Act: 1.0393. Min Act: -0.0000

Data Index: 698090 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.9674. Min Act: -0.0000

Data Index: 164198 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.8904. Min Act: -0.0000

Data Index: 1206471 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.9603. Min Act: -0.0000

Data Index: 1318240 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.8513. Min Act: -0.0000

Data Index: 1046533 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.8572. Min Act: -0.0000

Data Index: 453123 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.8416. Min Act: -0.0000

Data Index: 302367 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.8056. Min Act: -0.0000

Data Index: 403751 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.8552. Min Act: -0.0000

Data Index: 37513 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.8119. Min Act: -0.0000

Data Index: 557919 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.7799. Min Act: -0.0000

Data Index: 436093 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.8724. Min Act: -0.0000

Data Index: 106745 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.7006. Min Act: -0.0000

Data Index: 462405 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.8559. Min Act: -0.0000

Data Index: 1212783 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.8477. Min Act: -0.0000

Data Index: 87133 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.7559. Min Act: -0.0000

Data Index: 971215 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.6530. Min Act: -0.0000

Data Index: 1285004 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.8664. Min Act: -0.0000

Data Index: 1087417 (C4 (Web Text))

Max Activating Token Index: 202