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

Dataset: The Pile

Neuron 957 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.6400. Min Act: -0.0000

Data Index: 690195 (The Pile)

Max Activating Token Index: 65

Text #1

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.5405. Min Act: -0.0000

Data Index: 1159581 (The Pile)

Max Activating Token Index: 373

Text #2

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.5151. Min Act: -0.0000

Data Index: 1049623 (The Pile)

Max Activating Token Index: 967

Text #3

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.5684. Min Act: -0.0000

Data Index: 605756 (The Pile)

Max Activating Token Index: 550

Text #4

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4776. Min Act: -0.0000

Data Index: 886868 (The Pile)

Max Activating Token Index: 965

Text #5

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4944. Min Act: -0.0000

Data Index: 1998125 (The Pile)

Max Activating Token Index: 578

Text #6

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4101. Min Act: -0.0000

Data Index: 561627 (The Pile)

Max Activating Token Index: 547

Text #7

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4618. Min Act: -0.0000

Data Index: 591877 (The Pile)

Max Activating Token Index: 462

Text #8

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4745. Min Act: -0.0000

Data Index: 990987 (The Pile)

Max Activating Token Index: 360

Text #9

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4560. Min Act: -0.0000

Data Index: 1857281 (The Pile)

Max Activating Token Index: 824

Text #10

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4533. Min Act: -0.0000

Data Index: 1953962 (The Pile)

Max Activating Token Index: 206

Text #11

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4542. Min Act: -0.0000

Data Index: 1045095 (The Pile)

Max Activating Token Index: 300

Text #12

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4550. Min Act: -0.0000

Data Index: 1267514 (The Pile)

Max Activating Token Index: 415

Text #13

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4818. Min Act: -0.0000

Data Index: 1869317 (The Pile)

Max Activating Token Index: 431

Text #14

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4909. Min Act: -0.0000

Data Index: 531567 (The Pile)

Max Activating Token Index: 607

Text #15

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4502. Min Act: -0.0000

Data Index: 1751602 (The Pile)

Max Activating Token Index: 529

Text #16

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4156. Min Act: -0.0000

Data Index: 251693 (The Pile)

Max Activating Token Index: 685

Text #17

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4458. Min Act: -0.0000

Data Index: 303513 (The Pile)

Max Activating Token Index: 679

Text #18

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.3894. Min Act: -0.0000

Data Index: 1183698 (The Pile)

Max Activating Token Index: 98

Text #19

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.3863. Min Act: -0.0000

Data Index: 227646 (The Pile)

Max Activating Token Index: 874