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

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

Neuron 4388 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2694. Min Range: -3.2694

Max Act: 3.2648. Min Act: -0.0000

Data Index: 1590466 (Python Code)

Max Activating Token Index: 133

Text #1

Max Range: 3.2694. Min Range: -3.2694

Max Act: 3.2694. Min Act: -0.0000

Data Index: 117679 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 3.2694. Min Range: -3.2694

Max Act: 2.9162. Min Act: -0.0000

Data Index: 627279 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 3.2694. Min Range: -3.2694

Max Act: 2.8681. Min Act: -0.0000

Data Index: 294483 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 3.2694. Min Range: -3.2694

Max Act: 2.8213. Min Act: -0.0000

Data Index: 1306607 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 3.2694. Min Range: -3.2694

Max Act: 2.9420. Min Act: -0.0000

Data Index: 1297311 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 3.2694. Min Range: -3.2694

Max Act: 2.6939. Min Act: -0.0000

Data Index: 1588273 (Python Code)

Max Activating Token Index: 573

Text #7

Max Range: 3.2694. Min Range: -3.2694

Max Act: 2.6445. Min Act: -0.0000

Data Index: 1291280 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 3.2694. Min Range: -3.2694

Max Act: 2.5149. Min Act: -0.0000

Data Index: 256744 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 3.2694. Min Range: -3.2694

Max Act: 2.7300. Min Act: -0.0000

Data Index: 571660 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 3.2694. Min Range: -3.2694

Max Act: 2.6310. Min Act: -0.0000

Data Index: 138236 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 3.2694. Min Range: -3.2694

Max Act: 2.7413. Min Act: -0.0000

Data Index: 1251631 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 3.2694. Min Range: -3.2694

Max Act: 2.4766. Min Act: -0.0000

Data Index: 1550735 (Python Code)

Max Activating Token Index: 192

Text #13

Max Range: 3.2694. Min Range: -3.2694

Max Act: 2.5327. Min Act: -0.0000

Data Index: 184850 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 3.2694. Min Range: -3.2694

Max Act: 2.5771. Min Act: -0.0000

Data Index: 3453 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 3.2694. Min Range: -3.2694

Max Act: 2.5668. Min Act: -0.0000

Data Index: 1599637 (Python Code)

Max Activating Token Index: 589

Text #16

Max Range: 3.2694. Min Range: -3.2694

Max Act: 2.5348. Min Act: -0.0000

Data Index: 1566687 (Python Code)

Max Activating Token Index: 807

Text #17

Max Range: 3.2694. Min Range: -3.2694

Max Act: 2.6848. Min Act: -0.0000

Data Index: 321835 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 3.2694. Min Range: -3.2694

Max Act: 2.4060. Min Act: -0.0000

Data Index: 1182225 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 3.2694. Min Range: -3.2694

Max Act: 2.7655. Min Act: -0.0000

Data Index: 1532181 (Python Code)

Max Activating Token Index: 454