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

Dataset: The Pile

Neuron 3720 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: 0.5649. Min Range: -0.5649

Max Act: 0.5649. Min Act: -0.0000

Data Index: 930289 (The Pile)

Max Activating Token Index: 630

Text #1

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.5384. Min Act: -0.0000

Data Index: 114124 (The Pile)

Max Activating Token Index: 941

Text #2

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.5321. Min Act: -0.0000

Data Index: 1614951 (The Pile)

Max Activating Token Index: 854

Text #3

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.4807. Min Act: -0.0000

Data Index: 1938246 (The Pile)

Max Activating Token Index: 427

Text #4

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.4914. Min Act: -0.0000

Data Index: 1250114 (The Pile)

Max Activating Token Index: 1004

Text #5

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.4674. Min Act: -0.0000

Data Index: 1571339 (The Pile)

Max Activating Token Index: 1020

Text #6

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.4329. Min Act: -0.0000

Data Index: 128059 (The Pile)

Max Activating Token Index: 673

Text #7

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.4090. Min Act: -0.0000

Data Index: 576430 (The Pile)

Max Activating Token Index: 347

Text #8

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.4491. Min Act: -0.0000

Data Index: 1239225 (The Pile)

Max Activating Token Index: 359

Text #9

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.4248. Min Act: -0.0000

Data Index: 155047 (The Pile)

Max Activating Token Index: 125

Text #10

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.4231. Min Act: -0.0000

Data Index: 1942085 (The Pile)

Max Activating Token Index: 586

Text #11

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.4180. Min Act: -0.0000

Data Index: 1009634 (The Pile)

Max Activating Token Index: 456

Text #12

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.3914. Min Act: -0.0000

Data Index: 906276 (The Pile)

Max Activating Token Index: 217

Text #13

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.4027. Min Act: -0.0000

Data Index: 306293 (The Pile)

Max Activating Token Index: 902

Text #14

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.4314. Min Act: -0.0000

Data Index: 169459 (The Pile)

Max Activating Token Index: 142

Text #15

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.3990. Min Act: -0.0000

Data Index: 1232921 (The Pile)

Max Activating Token Index: 239

Text #16

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.3839. Min Act: -0.0000

Data Index: 415107 (The Pile)

Max Activating Token Index: 499

Text #17

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.3702. Min Act: -0.0000

Data Index: 487553 (The Pile)

Max Activating Token Index: 418

Text #18

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.3955. Min Act: -0.0000

Data Index: 1269281 (The Pile)

Max Activating Token Index: 241

Text #19

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.3954. Min Act: -0.0000

Data Index: 1221890 (The Pile)

Max Activating Token Index: 332