Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1338 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.5407. Min Range: -1.5407

Max Act: 1.5407. Min Act: -0.0000

Data Index: 1612277 (The Pile)

Max Activating Token Index: 927

Text #1

Max Range: 1.5407. Min Range: -1.5407

Max Act: 1.4059. Min Act: -0.0000

Data Index: 445416 (The Pile)

Max Activating Token Index: 90

Text #2

Max Range: 1.5407. Min Range: -1.5407

Max Act: 1.3538. Min Act: -0.0000

Data Index: 129185 (The Pile)

Max Activating Token Index: 574

Text #3

Max Range: 1.5407. Min Range: -1.5407

Max Act: 1.1311. Min Act: -0.0000

Data Index: 475259 (The Pile)

Max Activating Token Index: 155

Text #4

Max Range: 1.5407. Min Range: -1.5407

Max Act: 1.0871. Min Act: -0.0000

Data Index: 252722 (The Pile)

Max Activating Token Index: 150

Text #5

Max Range: 1.5407. Min Range: -1.5407

Max Act: 1.0779. Min Act: -0.0000

Data Index: 728129 (The Pile)

Max Activating Token Index: 236

Text #6

Max Range: 1.5407. Min Range: -1.5407

Max Act: 1.0534. Min Act: -0.0000

Data Index: 660376 (The Pile)

Max Activating Token Index: 264

Text #7

Max Range: 1.5407. Min Range: -1.5407

Max Act: 0.9725. Min Act: -0.0000

Data Index: 514166 (The Pile)

Max Activating Token Index: 733

Text #8

Max Range: 1.5407. Min Range: -1.5407

Max Act: 0.9390. Min Act: -0.0000

Data Index: 878927 (The Pile)

Max Activating Token Index: 399

Text #9

Max Range: 1.5407. Min Range: -1.5407

Max Act: 0.9911. Min Act: -0.0000

Data Index: 153254 (The Pile)

Max Activating Token Index: 625

Text #10

Max Range: 1.5407. Min Range: -1.5407

Max Act: 0.9221. Min Act: -0.0000

Data Index: 323415 (The Pile)

Max Activating Token Index: 196

Text #11

Max Range: 1.5407. Min Range: -1.5407

Max Act: 0.9135. Min Act: -0.0000

Data Index: 1950868 (The Pile)

Max Activating Token Index: 908

Text #12

Max Range: 1.5407. Min Range: -1.5407

Max Act: 0.9130. Min Act: -0.0000

Data Index: 1299629 (The Pile)

Max Activating Token Index: 613

Text #13

Max Range: 1.5407. Min Range: -1.5407

Max Act: 0.9062. Min Act: -0.0000

Data Index: 343876 (The Pile)

Max Activating Token Index: 365

Text #14

Max Range: 1.5407. Min Range: -1.5407

Max Act: 0.9653. Min Act: -0.0000

Data Index: 1868016 (The Pile)

Max Activating Token Index: 353

Text #15

Max Range: 1.5407. Min Range: -1.5407

Max Act: 0.9584. Min Act: -0.0000

Data Index: 1168461 (The Pile)

Max Activating Token Index: 861

Text #16

Max Range: 1.5407. Min Range: -1.5407

Max Act: 0.8985. Min Act: -0.0000

Data Index: 151846 (The Pile)

Max Activating Token Index: 31

Text #17

Max Range: 1.5407. Min Range: -1.5407

Max Act: 0.8842. Min Act: -0.0000

Data Index: 1801137 (The Pile)

Max Activating Token Index: 630

Text #18

Max Range: 1.5407. Min Range: -1.5407

Max Act: 0.8810. Min Act: -0.0000

Data Index: 1855818 (The Pile)

Max Activating Token Index: 442

Text #19

Max Range: 1.5407. Min Range: -1.5407

Max Act: 0.8138. Min Act: -0.0000

Data Index: 803622 (The Pile)

Max Activating Token Index: 115