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

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

Neuron 2086 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.5576. Min Act: -0.0002

Data Index: 674134 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.4873. Min Act: -0.0002

Data Index: 1150718 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.4916. Min Act: -0.0002

Data Index: 1213737 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.4864. Min Act: -0.0002

Data Index: 545937 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.4818. Min Act: -0.0002

Data Index: 241653 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.4784. Min Act: -0.0002

Data Index: 258140 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.4508. Min Act: -0.0002

Data Index: 1250682 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.4481. Min Act: -0.0002

Data Index: 786584 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.4284. Min Act: -0.0002

Data Index: 317560 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.4264. Min Act: -0.0002

Data Index: 13323 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.4280. Min Act: -0.0002

Data Index: 1354076 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.4123. Min Act: -0.0002

Data Index: 143258 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.3962. Min Act: -0.0002

Data Index: 1279596 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.4042. Min Act: -0.0002

Data Index: 1340138 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.4202. Min Act: -0.0002

Data Index: 491909 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.3997. Min Act: -0.0002

Data Index: 702993 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.3846. Min Act: -0.0002

Data Index: 1289476 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.3708. Min Act: -0.0002

Data Index: 316593 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.3818. Min Act: -0.0002

Data Index: 1299365 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.3602. Min Act: -0.0002

Data Index: 235978 (C4 (Web Text))

Max Activating Token Index: 954