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

Dataset: The Pile

Neuron 3693 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: 1.2064. Min Range: -1.2064

Max Act: 1.2064. Min Act: -0.0000

Data Index: 198397 (The Pile)

Max Activating Token Index: 457

Text #1

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.9705. Min Act: -0.0000

Data Index: 1308994 (The Pile)

Max Activating Token Index: 579

Text #2

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.8983. Min Act: -0.0000

Data Index: 511188 (The Pile)

Max Activating Token Index: 725

Text #3

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.8279. Min Act: -0.0000

Data Index: 1135733 (The Pile)

Max Activating Token Index: 891

Text #4

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.9871. Min Act: -0.0000

Data Index: 433033 (The Pile)

Max Activating Token Index: 809

Text #5

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.8750. Min Act: -0.0000

Data Index: 1453157 (The Pile)

Max Activating Token Index: 722

Text #6

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.8644. Min Act: -0.0000

Data Index: 1065178 (The Pile)

Max Activating Token Index: 83

Text #7

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.7356. Min Act: -0.0000

Data Index: 1431904 (The Pile)

Max Activating Token Index: 274

Text #8

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.6757. Min Act: -0.0000

Data Index: 791949 (The Pile)

Max Activating Token Index: 600

Text #9

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.7430. Min Act: -0.0000

Data Index: 13206 (The Pile)

Max Activating Token Index: 552

Text #10

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.7685. Min Act: -0.0000

Data Index: 594768 (The Pile)

Max Activating Token Index: 466

Text #11

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.7518. Min Act: -0.0000

Data Index: 685900 (The Pile)

Max Activating Token Index: 408

Text #12

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.7346. Min Act: -0.0000

Data Index: 1957181 (The Pile)

Max Activating Token Index: 280

Text #13

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.8665. Min Act: -0.0000

Data Index: 1691236 (The Pile)

Max Activating Token Index: 255

Text #14

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.7413. Min Act: -0.0000

Data Index: 1349044 (The Pile)

Max Activating Token Index: 517

Text #15

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.7250. Min Act: -0.0000

Data Index: 1439322 (The Pile)

Max Activating Token Index: 379

Text #16

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.7285. Min Act: -0.0000

Data Index: 1059663 (The Pile)

Max Activating Token Index: 480

Text #17

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.7373. Min Act: -0.0000

Data Index: 1471470 (The Pile)

Max Activating Token Index: 557

Text #18

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.7297. Min Act: -0.0000

Data Index: 1405658 (The Pile)

Max Activating Token Index: 683

Text #19

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.7484. Min Act: -0.0000

Data Index: 528109 (The Pile)

Max Activating Token Index: 309