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

Dataset: The Pile

Neuron 2441 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2469. Min Range: -5.2469

Max Act: 4.9295. Min Act: -0.0000

Data Index: 564599 (The Pile)

Max Activating Token Index: 623

Text #1

Max Range: 5.2469. Min Range: -5.2469

Max Act: 4.5361. Min Act: -0.0000

Data Index: 209735 (The Pile)

Max Activating Token Index: 431

Text #2

Max Range: 5.2469. Min Range: -5.2469

Max Act: 4.7725. Min Act: -0.0000

Data Index: 650556 (The Pile)

Max Activating Token Index: 69

Text #3

Max Range: 5.2469. Min Range: -5.2469

Max Act: 4.7746. Min Act: -0.0000

Data Index: 373663 (The Pile)

Max Activating Token Index: 962

Text #4

Max Range: 5.2469. Min Range: -5.2469

Max Act: 5.2469. Min Act: -0.0000

Data Index: 442550 (The Pile)

Max Activating Token Index: 896

Text #5

Max Range: 5.2469. Min Range: -5.2469

Max Act: 4.1751. Min Act: -0.0000

Data Index: 867800 (The Pile)

Max Activating Token Index: 639

Text #6

Max Range: 5.2469. Min Range: -5.2469

Max Act: 4.0044. Min Act: -0.0000

Data Index: 1333209 (The Pile)

Max Activating Token Index: 231

Text #7

Max Range: 5.2469. Min Range: -5.2469

Max Act: 4.0259. Min Act: -0.0000

Data Index: 1573138 (The Pile)

Max Activating Token Index: 804

Text #8

Max Range: 5.2469. Min Range: -5.2469

Max Act: 3.7496. Min Act: -0.0000

Data Index: 1216684 (The Pile)

Max Activating Token Index: 6

Text #9

Max Range: 5.2469. Min Range: -5.2469

Max Act: 3.5660. Min Act: -0.0000

Data Index: 1937297 (The Pile)

Max Activating Token Index: 234

Text #10

Max Range: 5.2469. Min Range: -5.2469

Max Act: 3.1716. Min Act: -0.0000

Data Index: 1541789 (The Pile)

Max Activating Token Index: 647

Text #11

Max Range: 5.2469. Min Range: -5.2469

Max Act: 3.0643. Min Act: -0.0000

Data Index: 1404044 (The Pile)

Max Activating Token Index: 700

Text #12

Max Range: 5.2469. Min Range: -5.2469

Max Act: 2.7844. Min Act: -0.0000

Data Index: 262422 (The Pile)

Max Activating Token Index: 293

Text #13

Max Range: 5.2469. Min Range: -5.2469

Max Act: 2.9041. Min Act: -0.0000

Data Index: 1217491 (The Pile)

Max Activating Token Index: 8

Text #14

Max Range: 5.2469. Min Range: -5.2469

Max Act: 2.8005. Min Act: -0.0000

Data Index: 1173789 (The Pile)

Max Activating Token Index: 417

Text #15

Max Range: 5.2469. Min Range: -5.2469

Max Act: 2.8291. Min Act: -0.0000

Data Index: 112252 (The Pile)

Max Activating Token Index: 147

Text #16

Max Range: 5.2469. Min Range: -5.2469

Max Act: 2.5760. Min Act: -0.0000

Data Index: 1016733 (The Pile)

Max Activating Token Index: 619

Text #17

Max Range: 5.2469. Min Range: -5.2469

Max Act: 2.5134. Min Act: -0.0000

Data Index: 221099 (The Pile)

Max Activating Token Index: 297

Text #18

Max Range: 5.2469. Min Range: -5.2469

Max Act: 2.9341. Min Act: -0.0000

Data Index: 1440774 (The Pile)

Max Activating Token Index: 394

Text #19

Max Range: 5.2469. Min Range: -5.2469

Max Act: 2.4539. Min Act: -0.0000

Data Index: 260588 (The Pile)

Max Activating Token Index: 870