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

Dataset: The Pile

Neuron 4043 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4539. Min Range: -1.4539

Max Act: 1.4539. Min Act: -0.0000

Data Index: 470813 (The Pile)

Max Activating Token Index: 83

Text #1

Max Range: 1.4539. Min Range: -1.4539

Max Act: 1.1345. Min Act: -0.0000

Data Index: 1760533 (The Pile)

Max Activating Token Index: 31

Text #2

Max Range: 1.4539. Min Range: -1.4539

Max Act: 0.9158. Min Act: -0.0000

Data Index: 1980843 (The Pile)

Max Activating Token Index: 108

Text #3

Max Range: 1.4539. Min Range: -1.4539

Max Act: 0.9594. Min Act: -0.0000

Data Index: 1512036 (The Pile)

Max Activating Token Index: 433

Text #4

Max Range: 1.4539. Min Range: -1.4539

Max Act: 0.7874. Min Act: -0.0000

Data Index: 1088790 (The Pile)

Max Activating Token Index: 183

Text #5

Max Range: 1.4539. Min Range: -1.4539

Max Act: 0.8446. Min Act: -0.0000

Data Index: 117393 (The Pile)

Max Activating Token Index: 252

Text #6

Max Range: 1.4539. Min Range: -1.4539

Max Act: 0.6920. Min Act: -0.0000

Data Index: 367541 (The Pile)

Max Activating Token Index: 524

Text #7

Max Range: 1.4539. Min Range: -1.4539

Max Act: 0.7538. Min Act: -0.0000

Data Index: 1249103 (The Pile)

Max Activating Token Index: 282

Text #8

Max Range: 1.4539. Min Range: -1.4539

Max Act: 0.8020. Min Act: -0.0000

Data Index: 1903665 (The Pile)

Max Activating Token Index: 482

Text #9

Max Range: 1.4539. Min Range: -1.4539

Max Act: 0.8019. Min Act: 0.0000

Data Index: 1129085 (The Pile)

Max Activating Token Index: 97

Text #10

Max Range: 1.4539. Min Range: -1.4539

Max Act: 0.6862. Min Act: -0.0000

Data Index: 1492307 (The Pile)

Max Activating Token Index: 687

Text #11

Max Range: 1.4539. Min Range: -1.4539

Max Act: 0.7007. Min Act: -0.0000

Data Index: 792193 (The Pile)

Max Activating Token Index: 357

Text #12

Max Range: 1.4539. Min Range: -1.4539

Max Act: 0.7392. Min Act: -0.0000

Data Index: 188379 (The Pile)

Max Activating Token Index: 587

Text #13

Max Range: 1.4539. Min Range: -1.4539

Max Act: 0.7021. Min Act: -0.0000

Data Index: 1200491 (The Pile)

Max Activating Token Index: 129

Text #14

Max Range: 1.4539. Min Range: -1.4539

Max Act: 0.6763. Min Act: -0.0000

Data Index: 207054 (The Pile)

Max Activating Token Index: 222

Text #15

Max Range: 1.4539. Min Range: -1.4539

Max Act: 0.6950. Min Act: -0.0000

Data Index: 1068602 (The Pile)

Max Activating Token Index: 534

Text #16

Max Range: 1.4539. Min Range: -1.4539

Max Act: 0.6766. Min Act: -0.0000

Data Index: 1598297 (The Pile)

Max Activating Token Index: 44

Text #17

Max Range: 1.4539. Min Range: -1.4539

Max Act: 0.6579. Min Act: -0.0000

Data Index: 1619765 (The Pile)

Max Activating Token Index: 615

Text #18

Max Range: 1.4539. Min Range: -1.4539

Max Act: 0.6907. Min Act: -0.0000

Data Index: 672541 (The Pile)

Max Activating Token Index: 269

Text #19

Max Range: 1.4539. Min Range: -1.4539

Max Act: 0.6447. Min Act: -0.0000

Data Index: 1195286 (The Pile)

Max Activating Token Index: 373