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

Dataset: The Pile

Neuron 909 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.7449. Min Act: -0.0000

Data Index: 260181 (The Pile)

Max Activating Token Index: 45

Text #1

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.6805. Min Act: -0.0000

Data Index: 912658 (The Pile)

Max Activating Token Index: 30

Text #2

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.6788. Min Act: -0.0000

Data Index: 1986064 (The Pile)

Max Activating Token Index: 209

Text #3

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5599. Min Act: -0.0000

Data Index: 285423 (The Pile)

Max Activating Token Index: 443

Text #4

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5689. Min Act: -0.0000

Data Index: 695310 (The Pile)

Max Activating Token Index: 764

Text #5

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5738. Min Act: -0.0000

Data Index: 1757510 (The Pile)

Max Activating Token Index: 493

Text #6

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5568. Min Act: -0.0000

Data Index: 1145117 (The Pile)

Max Activating Token Index: 695

Text #7

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5864. Min Act: -0.0000

Data Index: 387147 (The Pile)

Max Activating Token Index: 937

Text #8

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5511. Min Act: -0.0000

Data Index: 1825654 (The Pile)

Max Activating Token Index: 840

Text #9

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5578. Min Act: -0.0000

Data Index: 1386784 (The Pile)

Max Activating Token Index: 130

Text #10

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5423. Min Act: -0.0000

Data Index: 890074 (The Pile)

Max Activating Token Index: 308

Text #11

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5520. Min Act: -0.0000

Data Index: 788948 (The Pile)

Max Activating Token Index: 854

Text #12

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5096. Min Act: -0.0000

Data Index: 1429900 (The Pile)

Max Activating Token Index: 319

Text #13

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5297. Min Act: -0.0000

Data Index: 1715259 (The Pile)

Max Activating Token Index: 625

Text #14

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5452. Min Act: -0.0000

Data Index: 381056 (The Pile)

Max Activating Token Index: 28

Text #15

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5286. Min Act: -0.0000

Data Index: 878624 (The Pile)

Max Activating Token Index: 676

Text #16

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5407. Min Act: -0.0000

Data Index: 1036811 (The Pile)

Max Activating Token Index: 685

Text #17

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5254. Min Act: -0.0000

Data Index: 105079 (The Pile)

Max Activating Token Index: 103

Text #18

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5113. Min Act: -0.0000

Data Index: 1677492 (The Pile)

Max Activating Token Index: 13

Text #19

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5405. Min Act: -0.0000

Data Index: 1630611 (The Pile)

Max Activating Token Index: 322