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

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

Neuron 1843 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2673. Min Range: -1.2673

Max Act: 1.1860. Min Act: -0.0004

Data Index: 491218 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 1.2673. Min Range: -1.2673

Max Act: 0.9495. Min Act: -0.0004

Data Index: 7684 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 1.2673. Min Range: -1.2673

Max Act: 1.2252. Min Act: -0.0004

Data Index: 61678 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 1.2673. Min Range: -1.2673

Max Act: 0.9369. Min Act: -0.0004

Data Index: 841200 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 1.2673. Min Range: -1.2673

Max Act: 1.1542. Min Act: -0.0004

Data Index: 142910 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 1.2673. Min Range: -1.2673

Max Act: 0.9835. Min Act: -0.0004

Data Index: 653888 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 1.2673. Min Range: -1.2673

Max Act: 1.2656. Min Act: -0.0004

Data Index: 1334969 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 1.2673. Min Range: -1.2673

Max Act: 1.2191. Min Act: -0.0004

Data Index: 537059 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 1.2673. Min Range: -1.2673

Max Act: 1.0553. Min Act: -0.0004

Data Index: 34550 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 1.2673. Min Range: -1.2673

Max Act: 1.0833. Min Act: -0.0004

Data Index: 417230 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 1.2673. Min Range: -1.2673

Max Act: 1.0503. Min Act: -0.0004

Data Index: 135548 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 1.2673. Min Range: -1.2673

Max Act: 1.2079. Min Act: -0.0004

Data Index: 1340973 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 1.2673. Min Range: -1.2673

Max Act: 1.1729. Min Act: -0.0004

Data Index: 491442 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 1.2673. Min Range: -1.2673

Max Act: 1.0411. Min Act: -0.0004

Data Index: 975537 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 1.2673. Min Range: -1.2673

Max Act: 1.1672. Min Act: -0.0004

Data Index: 1341723 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 1.2673. Min Range: -1.2673

Max Act: 1.2673. Min Act: -0.0004

Data Index: 1440128 (Python Code)

Max Activating Token Index: 619

Text #16

Max Range: 1.2673. Min Range: -1.2673

Max Act: 1.1257. Min Act: -0.0004

Data Index: 610767 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 1.2673. Min Range: -1.2673

Max Act: 1.2497. Min Act: -0.0004

Data Index: 905834 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 1.2673. Min Range: -1.2673

Max Act: 1.0831. Min Act: -0.0004

Data Index: 905718 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 1.2673. Min Range: -1.2673

Max Act: 1.1694. Min Act: -0.0004

Data Index: 1215486 (C4 (Web Text))

Max Activating Token Index: 201