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

Dataset: The Pile

Neuron 355 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: 1.5814. Min Range: -1.5814

Max Act: 1.5814. Min Act: -0.0000

Data Index: 1676642 (The Pile)

Max Activating Token Index: 674

Text #1

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.4115. Min Act: -0.0000

Data Index: 1108695 (The Pile)

Max Activating Token Index: 404

Text #2

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.3598. Min Act: -0.0000

Data Index: 1690363 (The Pile)

Max Activating Token Index: 488

Text #3

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.3319. Min Act: -0.0000

Data Index: 733361 (The Pile)

Max Activating Token Index: 187

Text #4

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.2484. Min Act: -0.0000

Data Index: 185716 (The Pile)

Max Activating Token Index: 527

Text #5

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.3434. Min Act: -0.0000

Data Index: 1724956 (The Pile)

Max Activating Token Index: 316

Text #6

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.1521. Min Act: -0.0000

Data Index: 45426 (The Pile)

Max Activating Token Index: 991

Text #7

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.1005. Min Act: -0.0000

Data Index: 1041081 (The Pile)

Max Activating Token Index: 354

Text #8

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.1000. Min Act: -0.0000

Data Index: 1656706 (The Pile)

Max Activating Token Index: 183

Text #9

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.1375. Min Act: -0.0000

Data Index: 485501 (The Pile)

Max Activating Token Index: 151

Text #10

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.1353. Min Act: -0.0000

Data Index: 783944 (The Pile)

Max Activating Token Index: 503

Text #11

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.0036. Min Act: -0.0000

Data Index: 241672 (The Pile)

Max Activating Token Index: 538

Text #12

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.1966. Min Act: -0.0000

Data Index: 531537 (The Pile)

Max Activating Token Index: 791

Text #13

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.0501. Min Act: -0.0000

Data Index: 1261963 (The Pile)

Max Activating Token Index: 186

Text #14

Max Range: 1.5814. Min Range: -1.5814

Max Act: 0.9479. Min Act: -0.0000

Data Index: 1365757 (The Pile)

Max Activating Token Index: 962

Text #15

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.0162. Min Act: -0.0000

Data Index: 916340 (The Pile)

Max Activating Token Index: 353

Text #16

Max Range: 1.5814. Min Range: -1.5814

Max Act: 0.9799. Min Act: -0.0000

Data Index: 1989366 (The Pile)

Max Activating Token Index: 49

Text #17

Max Range: 1.5814. Min Range: -1.5814

Max Act: 0.9377. Min Act: 0.0000

Data Index: 861678 (The Pile)

Max Activating Token Index: 152

Text #18

Max Range: 1.5814. Min Range: -1.5814

Max Act: 0.9371. Min Act: -0.0000

Data Index: 863686 (The Pile)

Max Activating Token Index: 928

Text #19

Max Range: 1.5814. Min Range: -1.5814

Max Act: 0.9888. Min Act: -0.0000

Data Index: 1244469 (The Pile)

Max Activating Token Index: 853