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

Dataset: The Pile

Neuron 164 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: 1.6075. Min Range: -1.6075

Max Act: 1.6075. Min Act: -0.0000

Data Index: 1983207 (The Pile)

Max Activating Token Index: 68

Text #1

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.5467. Min Act: -0.0000

Data Index: 626856 (The Pile)

Max Activating Token Index: 356

Text #2

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.4098. Min Act: -0.0000

Data Index: 1537915 (The Pile)

Max Activating Token Index: 558

Text #3

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.2876. Min Act: -0.0000

Data Index: 1791081 (The Pile)

Max Activating Token Index: 324

Text #4

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.2299. Min Act: -0.0000

Data Index: 286495 (The Pile)

Max Activating Token Index: 143

Text #5

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.3629. Min Act: -0.0000

Data Index: 1238276 (The Pile)

Max Activating Token Index: 1004

Text #6

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.1387. Min Act: -0.0000

Data Index: 482855 (The Pile)

Max Activating Token Index: 834

Text #7

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.1780. Min Act: -0.0000

Data Index: 1253446 (The Pile)

Max Activating Token Index: 842

Text #8

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.1010. Min Act: -0.0000

Data Index: 1530959 (The Pile)

Max Activating Token Index: 906

Text #9

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.1335. Min Act: -0.0000

Data Index: 725456 (The Pile)

Max Activating Token Index: 453

Text #10

Max Range: 1.6075. Min Range: -1.6075

Max Act: 0.9594. Min Act: -0.0000

Data Index: 43606 (The Pile)

Max Activating Token Index: 998

Text #11

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.1161. Min Act: -0.0000

Data Index: 1371586 (The Pile)

Max Activating Token Index: 931

Text #12

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.0715. Min Act: -0.0000

Data Index: 168630 (The Pile)

Max Activating Token Index: 867

Text #13

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.1107. Min Act: -0.0000

Data Index: 553182 (The Pile)

Max Activating Token Index: 521

Text #14

Max Range: 1.6075. Min Range: -1.6075

Max Act: 0.9709. Min Act: -0.0000

Data Index: 1408529 (The Pile)

Max Activating Token Index: 691

Text #15

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.0266. Min Act: -0.0000

Data Index: 223347 (The Pile)

Max Activating Token Index: 768

Text #16

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.1436. Min Act: -0.0000

Data Index: 245641 (The Pile)

Max Activating Token Index: 374

Text #17

Max Range: 1.6075. Min Range: -1.6075

Max Act: 0.8784. Min Act: -0.0000

Data Index: 1824080 (The Pile)

Max Activating Token Index: 845

Text #18

Max Range: 1.6075. Min Range: -1.6075

Max Act: 0.9442. Min Act: -0.0000

Data Index: 1391452 (The Pile)

Max Activating Token Index: 996

Text #19

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.0970. Min Act: -0.0000

Data Index: 840648 (The Pile)

Max Activating Token Index: 89