Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1104 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.5887. Min Range: -3.5887

Max Act: 3.5887. Min Act: -0.0000

Data Index: 741352 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 3.5887. Min Range: -3.5887

Max Act: 2.0731. Min Act: -0.0000

Data Index: 565366 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 3.5887. Min Range: -3.5887

Max Act: 2.0387. Min Act: -0.0000

Data Index: 867922 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 3.5887. Min Range: -3.5887

Max Act: 1.9811. Min Act: -0.0000

Data Index: 325043 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 3.5887. Min Range: -3.5887

Max Act: 1.8465. Min Act: -0.0000

Data Index: 706742 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 3.5887. Min Range: -3.5887

Max Act: 1.8059. Min Act: -0.0000

Data Index: 161272 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 3.5887. Min Range: -3.5887

Max Act: 1.6815. Min Act: -0.0001

Data Index: 1282797 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 3.5887. Min Range: -3.5887

Max Act: 1.6917. Min Act: -0.0001

Data Index: 22179 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 3.5887. Min Range: -3.5887

Max Act: 1.6522. Min Act: -0.0000

Data Index: 1144613 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 3.5887. Min Range: -3.5887

Max Act: 1.5230. Min Act: -0.0000

Data Index: 656812 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 3.5887. Min Range: -3.5887

Max Act: 1.6061. Min Act: -0.0000

Data Index: 448582 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 3.5887. Min Range: -3.5887

Max Act: 1.5588. Min Act: -0.0000

Data Index: 710249 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 3.5887. Min Range: -3.5887

Max Act: 1.5269. Min Act: -0.0000

Data Index: 24992 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 3.5887. Min Range: -3.5887

Max Act: 1.5703. Min Act: -0.0000

Data Index: 160354 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 3.5887. Min Range: -3.5887

Max Act: 1.5657. Min Act: -0.0000

Data Index: 471427 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 3.5887. Min Range: -3.5887

Max Act: 1.4778. Min Act: -0.0000

Data Index: 760631 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 3.5887. Min Range: -3.5887

Max Act: 1.5841. Min Act: -0.0001

Data Index: 746317 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 3.5887. Min Range: -3.5887

Max Act: 1.4381. Min Act: -0.0000

Data Index: 1304998 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 3.5887. Min Range: -3.5887

Max Act: 1.4419. Min Act: -0.0000

Data Index: 811311 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 3.5887. Min Range: -3.5887

Max Act: 1.4408. Min Act: -0.0000

Data Index: 377455 (C4 (Web Text))

Max Activating Token Index: 554