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

Dataset: The Pile

Neuron 4555 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: 1.3536. Min Range: -1.3536

Max Act: 1.3536. Min Act: -0.0000

Data Index: 923360 (The Pile)

Max Activating Token Index: 104

Text #1

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.3201. Min Act: -0.0000

Data Index: 1411361 (The Pile)

Max Activating Token Index: 883

Text #2

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1671. Min Act: -0.0000

Data Index: 667283 (The Pile)

Max Activating Token Index: 88

Text #3

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.2274. Min Act: -0.0000

Data Index: 1901434 (The Pile)

Max Activating Token Index: 448

Text #4

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.2312. Min Act: -0.0000

Data Index: 304997 (The Pile)

Max Activating Token Index: 773

Text #5

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.2006. Min Act: -0.0000

Data Index: 695007 (The Pile)

Max Activating Token Index: 935

Text #6

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1296. Min Act: -0.0000

Data Index: 1820486 (The Pile)

Max Activating Token Index: 877

Text #7

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1955. Min Act: -0.0000

Data Index: 1313764 (The Pile)

Max Activating Token Index: 540

Text #8

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.0212. Min Act: -0.0000

Data Index: 284890 (The Pile)

Max Activating Token Index: 458

Text #9

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.0863. Min Act: -0.0000

Data Index: 62382 (The Pile)

Max Activating Token Index: 739

Text #10

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.0913. Min Act: -0.0000

Data Index: 924355 (The Pile)

Max Activating Token Index: 676

Text #11

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1408. Min Act: -0.0000

Data Index: 1518706 (The Pile)

Max Activating Token Index: 230

Text #12

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.0145. Min Act: -0.0000

Data Index: 663191 (The Pile)

Max Activating Token Index: 157

Text #13

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.0026. Min Act: -0.0000

Data Index: 443579 (The Pile)

Max Activating Token Index: 559

Text #14

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.0552. Min Act: -0.0000

Data Index: 993845 (The Pile)

Max Activating Token Index: 225

Text #15

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.0619. Min Act: -0.0000

Data Index: 359575 (The Pile)

Max Activating Token Index: 50

Text #16

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.0540. Min Act: -0.0000

Data Index: 240465 (The Pile)

Max Activating Token Index: 529

Text #17

Max Range: 1.3536. Min Range: -1.3536

Max Act: 0.9779. Min Act: -0.0000

Data Index: 505690 (The Pile)

Max Activating Token Index: 177

Text #18

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.0502. Min Act: -0.0000

Data Index: 940275 (The Pile)

Max Activating Token Index: 558

Text #19

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.0388. Min Act: -0.0000

Data Index: 1316838 (The Pile)

Max Activating Token Index: 589