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

Dataset: The Pile

Neuron 789 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: 3.7744. Min Range: -3.7744

Max Act: 3.7744. Min Act: -0.0000

Data Index: 1604532 (The Pile)

Max Activating Token Index: 536

Text #1

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.9231. Min Act: -0.0000

Data Index: 46729 (The Pile)

Max Activating Token Index: 286

Text #2

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.8660. Min Act: -0.0000

Data Index: 1590478 (The Pile)

Max Activating Token Index: 419

Text #3

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.6437. Min Act: -0.0000

Data Index: 935870 (The Pile)

Max Activating Token Index: 615

Text #4

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.6429. Min Act: -0.0000

Data Index: 1382088 (The Pile)

Max Activating Token Index: 492

Text #5

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.5436. Min Act: -0.0000

Data Index: 1720852 (The Pile)

Max Activating Token Index: 917

Text #6

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.8504. Min Act: -0.0000

Data Index: 1457801 (The Pile)

Max Activating Token Index: 654

Text #7

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.7152. Min Act: -0.0000

Data Index: 1078907 (The Pile)

Max Activating Token Index: 872

Text #8

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.3691. Min Act: -0.0000

Data Index: 931053 (The Pile)

Max Activating Token Index: 773

Text #9

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.5680. Min Act: -0.0000

Data Index: 119428 (The Pile)

Max Activating Token Index: 584

Text #10

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.5568. Min Act: -0.0000

Data Index: 423453 (The Pile)

Max Activating Token Index: 550

Text #11

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.4709. Min Act: -0.0000

Data Index: 745171 (The Pile)

Max Activating Token Index: 450

Text #12

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.8547. Min Act: -0.0000

Data Index: 1039284 (The Pile)

Max Activating Token Index: 639

Text #13

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.4070. Min Act: -0.0000

Data Index: 910759 (The Pile)

Max Activating Token Index: 633

Text #14

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.3613. Min Act: -0.0000

Data Index: 1935718 (The Pile)

Max Activating Token Index: 150

Text #15

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.4658. Min Act: -0.0000

Data Index: 202734 (The Pile)

Max Activating Token Index: 723

Text #16

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.6477. Min Act: -0.0000

Data Index: 1922261 (The Pile)

Max Activating Token Index: 227

Text #17

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.4082. Min Act: -0.0000

Data Index: 1466835 (The Pile)

Max Activating Token Index: 866

Text #18

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.5230. Min Act: -0.0000

Data Index: 1147101 (The Pile)

Max Activating Token Index: 411

Text #19

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.4483. Min Act: -0.0000

Data Index: 661203 (The Pile)

Max Activating Token Index: 931