Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 180 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.4239. Min Act: -0.0000

Data Index: 578941 (The Pile)

Max Activating Token Index: 608

Text #1

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3702. Min Act: -0.0000

Data Index: 161273 (The Pile)

Max Activating Token Index: 624

Text #2

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3793. Min Act: -0.0000

Data Index: 315641 (The Pile)

Max Activating Token Index: 842

Text #3

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3196. Min Act: -0.0000

Data Index: 1793669 (The Pile)

Max Activating Token Index: 618

Text #4

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3319. Min Act: -0.0000

Data Index: 353188 (The Pile)

Max Activating Token Index: 850

Text #5

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.2879. Min Act: -0.0000

Data Index: 730458 (The Pile)

Max Activating Token Index: 362

Text #6

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.2836. Min Act: -0.0000

Data Index: 797232 (The Pile)

Max Activating Token Index: 255

Text #7

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.2704. Min Act: -0.0000

Data Index: 364557 (The Pile)

Max Activating Token Index: 323

Text #8

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.2667. Min Act: -0.0000

Data Index: 1218513 (The Pile)

Max Activating Token Index: 109

Text #9

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.2735. Min Act: -0.0000

Data Index: 1939101 (The Pile)

Max Activating Token Index: 626

Text #10

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.2625. Min Act: -0.0000

Data Index: 1976983 (The Pile)

Max Activating Token Index: 67

Text #11

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.2892. Min Act: -0.0000

Data Index: 880002 (The Pile)

Max Activating Token Index: 860

Text #12

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.2490. Min Act: -0.0000

Data Index: 1422595 (The Pile)

Max Activating Token Index: 782

Text #13

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.2599. Min Act: -0.0000

Data Index: 1940381 (The Pile)

Max Activating Token Index: 764

Text #14

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.2756. Min Act: -0.0000

Data Index: 549815 (The Pile)

Max Activating Token Index: 491

Text #15

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.2450. Min Act: -0.0000

Data Index: 838941 (The Pile)

Max Activating Token Index: 712

Text #16

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.2498. Min Act: -0.0000

Data Index: 1047998 (The Pile)

Max Activating Token Index: 730

Text #17

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.2520. Min Act: -0.0000

Data Index: 504127 (The Pile)

Max Activating Token Index: 597

Text #18

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.2373. Min Act: -0.0000

Data Index: 1504638 (The Pile)

Max Activating Token Index: 806

Text #19

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.2519. Min Act: -0.0000

Data Index: 411004 (The Pile)

Max Activating Token Index: 771