Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2007 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.6858. Min Act: -0.0001

Data Index: 107618 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.5432. Min Act: -0.0001

Data Index: 1019386 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.5717. Min Act: -0.0001

Data Index: 820331 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.5313. Min Act: -0.0001

Data Index: 891739 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.4863. Min Act: -0.0001

Data Index: 172930 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.5392. Min Act: -0.0001

Data Index: 949805 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.4715. Min Act: -0.0001

Data Index: 414865 (C4 (Web Text))

Max Activating Token Index: 924

Text #7

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.4987. Min Act: -0.0001

Data Index: 1299051 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.4624. Min Act: -0.0001

Data Index: 327368 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.4678. Min Act: -0.0001

Data Index: 820116 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.4520. Min Act: -0.0001

Data Index: 711486 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.4902. Min Act: -0.0001

Data Index: 1032600 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.4588. Min Act: -0.0001

Data Index: 337023 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.4666. Min Act: -0.0001

Data Index: 1184600 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.3255. Min Act: -0.0001

Data Index: 216974 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.4467. Min Act: -0.0001

Data Index: 37889 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.4650. Min Act: -0.0001

Data Index: 1315621 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.3809. Min Act: -0.0001

Data Index: 29142 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.4417. Min Act: -0.0001

Data Index: 171277 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.4236. Min Act: -0.0001

Data Index: 1320212 (C4 (Web Text))

Max Activating Token Index: 898