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

Dataset: The Pile

Neuron 4050 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: 0.4726. Min Range: -0.4726

Max Act: 0.4726. Min Act: -0.0000

Data Index: 1690675 (The Pile)

Max Activating Token Index: 502

Text #1

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3937. Min Act: -0.0000

Data Index: 332686 (The Pile)

Max Activating Token Index: 680

Text #2

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3880. Min Act: -0.0000

Data Index: 495571 (The Pile)

Max Activating Token Index: 168

Text #3

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3829. Min Act: -0.0000

Data Index: 45794 (The Pile)

Max Activating Token Index: 360

Text #4

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3994. Min Act: -0.0000

Data Index: 801064 (The Pile)

Max Activating Token Index: 680

Text #5

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3889. Min Act: -0.0000

Data Index: 1111312 (The Pile)

Max Activating Token Index: 466

Text #6

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3524. Min Act: -0.0000

Data Index: 1223005 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3921. Min Act: -0.0000

Data Index: 894041 (The Pile)

Max Activating Token Index: 412

Text #8

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3970. Min Act: -0.0000

Data Index: 221295 (The Pile)

Max Activating Token Index: 664

Text #9

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3554. Min Act: -0.0000

Data Index: 331053 (The Pile)

Max Activating Token Index: 177

Text #10

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3658. Min Act: -0.0000

Data Index: 377789 (The Pile)

Max Activating Token Index: 732

Text #11

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3422. Min Act: -0.0000

Data Index: 1933809 (The Pile)

Max Activating Token Index: 477

Text #12

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3628. Min Act: -0.0000

Data Index: 136597 (The Pile)

Max Activating Token Index: 259

Text #13

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3596. Min Act: -0.0000

Data Index: 1209865 (The Pile)

Max Activating Token Index: 639

Text #14

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3912. Min Act: -0.0000

Data Index: 368872 (The Pile)

Max Activating Token Index: 615

Text #15

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3330. Min Act: -0.0000

Data Index: 597947 (The Pile)

Max Activating Token Index: 609

Text #16

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3477. Min Act: -0.0000

Data Index: 1815253 (The Pile)

Max Activating Token Index: 51

Text #17

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3562. Min Act: -0.0000

Data Index: 1972435 (The Pile)

Max Activating Token Index: 928

Text #18

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3485. Min Act: -0.0000

Data Index: 666025 (The Pile)

Max Activating Token Index: 159

Text #19

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3530. Min Act: -0.0000

Data Index: 1548825 (The Pile)

Max Activating Token Index: 212