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

Dataset: The Pile

Neuron 2588 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.9129. Min Act: -0.0000

Data Index: 262550 (The Pile)

Max Activating Token Index: 995

Text #1

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.7237. Min Act: -0.0000

Data Index: 784901 (The Pile)

Max Activating Token Index: 670

Text #2

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.8021. Min Act: -0.0000

Data Index: 845392 (The Pile)

Max Activating Token Index: 1014

Text #3

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.6469. Min Act: 0.0000

Data Index: 872624 (The Pile)

Max Activating Token Index: 829

Text #4

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.7054. Min Act: -0.0000

Data Index: 1378862 (The Pile)

Max Activating Token Index: 963

Text #5

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.7769. Min Act: -0.0000

Data Index: 701677 (The Pile)

Max Activating Token Index: 277

Text #6

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.6475. Min Act: 0.0000

Data Index: 1864826 (The Pile)

Max Activating Token Index: 582

Text #7

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.6668. Min Act: -0.0000

Data Index: 1815769 (The Pile)

Max Activating Token Index: 963

Text #8

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.6237. Min Act: -0.0000

Data Index: 347975 (The Pile)

Max Activating Token Index: 447

Text #9

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.6452. Min Act: -0.0000

Data Index: 1487709 (The Pile)

Max Activating Token Index: 325

Text #10

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.6848. Min Act: 0.0000

Data Index: 259326 (The Pile)

Max Activating Token Index: 612

Text #11

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.6705. Min Act: 0.0000

Data Index: 139083 (The Pile)

Max Activating Token Index: 802

Text #12

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.6142. Min Act: 0.0000

Data Index: 1760753 (The Pile)

Max Activating Token Index: 132

Text #13

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.6145. Min Act: -0.0000

Data Index: 709612 (The Pile)

Max Activating Token Index: 43

Text #14

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.6543. Min Act: -0.0000

Data Index: 1929596 (The Pile)

Max Activating Token Index: 571

Text #15

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.6069. Min Act: -0.0000

Data Index: 41479 (The Pile)

Max Activating Token Index: 383

Text #16

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.6030. Min Act: -0.0000

Data Index: 718632 (The Pile)

Max Activating Token Index: 415

Text #17

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.5860. Min Act: -0.0000

Data Index: 791600 (The Pile)

Max Activating Token Index: 222

Text #18

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.5994. Min Act: -0.0000

Data Index: 1349960 (The Pile)

Max Activating Token Index: 682

Text #19

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.6308. Min Act: -0.0000

Data Index: 398310 (The Pile)

Max Activating Token Index: 963