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

Dataset: The Pile

Neuron 3585 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: 1.0771. Min Range: -1.0771

Max Act: 1.0771. Min Act: -0.0000

Data Index: 1629244 (The Pile)

Max Activating Token Index: 935

Text #1

Max Range: 1.0771. Min Range: -1.0771

Max Act: 1.0062. Min Act: -0.0000

Data Index: 507343 (The Pile)

Max Activating Token Index: 1008

Text #2

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.8853. Min Act: -0.0000

Data Index: 1062618 (The Pile)

Max Activating Token Index: 152

Text #3

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.8559. Min Act: -0.0000

Data Index: 576134 (The Pile)

Max Activating Token Index: 375

Text #4

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.8491. Min Act: -0.0000

Data Index: 438039 (The Pile)

Max Activating Token Index: 283

Text #5

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.8179. Min Act: -0.0000

Data Index: 1495948 (The Pile)

Max Activating Token Index: 884

Text #6

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.8341. Min Act: -0.0000

Data Index: 1882848 (The Pile)

Max Activating Token Index: 232

Text #7

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.8237. Min Act: -0.0000

Data Index: 954391 (The Pile)

Max Activating Token Index: 1014

Text #8

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.8050. Min Act: -0.0000

Data Index: 359352 (The Pile)

Max Activating Token Index: 765

Text #9

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.7810. Min Act: -0.0000

Data Index: 1654860 (The Pile)

Max Activating Token Index: 763

Text #10

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.7971. Min Act: -0.0000

Data Index: 1066725 (The Pile)

Max Activating Token Index: 636

Text #11

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.7688. Min Act: -0.0000

Data Index: 669303 (The Pile)

Max Activating Token Index: 267

Text #12

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.7865. Min Act: -0.0000

Data Index: 771268 (The Pile)

Max Activating Token Index: 624

Text #13

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.7814. Min Act: -0.0000

Data Index: 791482 (The Pile)

Max Activating Token Index: 255

Text #14

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.7768. Min Act: -0.0000

Data Index: 1143214 (The Pile)

Max Activating Token Index: 699

Text #15

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.7938. Min Act: -0.0000

Data Index: 318151 (The Pile)

Max Activating Token Index: 436

Text #16

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.7742. Min Act: -0.0000

Data Index: 1663658 (The Pile)

Max Activating Token Index: 169

Text #17

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.7471. Min Act: -0.0000

Data Index: 1831571 (The Pile)

Max Activating Token Index: 185

Text #18

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.7655. Min Act: -0.0000

Data Index: 927741 (The Pile)

Max Activating Token Index: 532

Text #19

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.7647. Min Act: -0.0000

Data Index: 335853 (The Pile)

Max Activating Token Index: 31