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

Dataset: The Pile

Neuron 4229 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0444. Min Range: -3.0444

Max Act: 3.0444. Min Act: -0.0000

Data Index: 72991 (The Pile)

Max Activating Token Index: 742

Text #1

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.7312. Min Act: -0.0000

Data Index: 1155243 (The Pile)

Max Activating Token Index: 76

Text #2

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.8223. Min Act: -0.0000

Data Index: 1619282 (The Pile)

Max Activating Token Index: 323

Text #3

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.7559. Min Act: -0.0000

Data Index: 1426223 (The Pile)

Max Activating Token Index: 170

Text #4

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.5743. Min Act: -0.0000

Data Index: 1984431 (The Pile)

Max Activating Token Index: 162

Text #5

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.4079. Min Act: -0.0000

Data Index: 805705 (The Pile)

Max Activating Token Index: 228

Text #6

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.4880. Min Act: -0.0000

Data Index: 1586861 (The Pile)

Max Activating Token Index: 54

Text #7

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.2347. Min Act: -0.0000

Data Index: 1606840 (The Pile)

Max Activating Token Index: 221

Text #8

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.5449. Min Act: -0.0000

Data Index: 1391984 (The Pile)

Max Activating Token Index: 992

Text #9

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.2890. Min Act: -0.0000

Data Index: 587643 (The Pile)

Max Activating Token Index: 78

Text #10

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.3721. Min Act: -0.0000

Data Index: 1659712 (The Pile)

Max Activating Token Index: 573

Text #11

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.2383. Min Act: -0.0000

Data Index: 1695116 (The Pile)

Max Activating Token Index: 407

Text #12

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.3566. Min Act: -0.0000

Data Index: 1490562 (The Pile)

Max Activating Token Index: 623

Text #13

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.3692. Min Act: -0.0000

Data Index: 251999 (The Pile)

Max Activating Token Index: 992

Text #14

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.3462. Min Act: -0.0000

Data Index: 1918885 (The Pile)

Max Activating Token Index: 56

Text #15

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.4356. Min Act: -0.0000

Data Index: 1560777 (The Pile)

Max Activating Token Index: 640

Text #16

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.2735. Min Act: -0.0000

Data Index: 1011682 (The Pile)

Max Activating Token Index: 334

Text #17

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.2589. Min Act: -0.0000

Data Index: 396064 (The Pile)

Max Activating Token Index: 512

Text #18

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.1266. Min Act: -0.0000

Data Index: 1131315 (The Pile)

Max Activating Token Index: 861

Text #19

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.3737. Min Act: -0.0000

Data Index: 1993348 (The Pile)

Max Activating Token Index: 252