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

Dataset: The Pile

Neuron 1923 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2129. Min Range: -1.2129

Max Act: 1.2129. Min Act: -0.0000

Data Index: 1074387 (The Pile)

Max Activating Token Index: 505

Text #1

Max Range: 1.2129. Min Range: -1.2129

Max Act: 1.1190. Min Act: -0.0000

Data Index: 891598 (The Pile)

Max Activating Token Index: 223

Text #2

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.8469. Min Act: -0.0000

Data Index: 1951568 (The Pile)

Max Activating Token Index: 733

Text #3

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.9558. Min Act: -0.0000

Data Index: 688499 (The Pile)

Max Activating Token Index: 192

Text #4

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.9241. Min Act: -0.0000

Data Index: 1628860 (The Pile)

Max Activating Token Index: 106

Text #5

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.9549. Min Act: -0.0000

Data Index: 1256455 (The Pile)

Max Activating Token Index: 435

Text #6

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.9315. Min Act: -0.0000

Data Index: 1800671 (The Pile)

Max Activating Token Index: 362

Text #7

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.8241. Min Act: -0.0000

Data Index: 1672268 (The Pile)

Max Activating Token Index: 142

Text #8

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.8991. Min Act: -0.0000

Data Index: 86126 (The Pile)

Max Activating Token Index: 295

Text #9

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.9751. Min Act: -0.0000

Data Index: 298508 (The Pile)

Max Activating Token Index: 271

Text #10

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.9191. Min Act: -0.0000

Data Index: 328134 (The Pile)

Max Activating Token Index: 190

Text #11

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.9706. Min Act: -0.0000

Data Index: 210536 (The Pile)

Max Activating Token Index: 250

Text #12

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.8638. Min Act: -0.0000

Data Index: 71679 (The Pile)

Max Activating Token Index: 878

Text #13

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.8485. Min Act: -0.0000

Data Index: 48505 (The Pile)

Max Activating Token Index: 597

Text #14

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.9659. Min Act: -0.0000

Data Index: 1461315 (The Pile)

Max Activating Token Index: 184

Text #15

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.8924. Min Act: -0.0000

Data Index: 1401710 (The Pile)

Max Activating Token Index: 223

Text #16

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.7673. Min Act: -0.0000

Data Index: 789370 (The Pile)

Max Activating Token Index: 293

Text #17

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.8956. Min Act: -0.0000

Data Index: 221037 (The Pile)

Max Activating Token Index: 190

Text #18

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.8657. Min Act: -0.0000

Data Index: 1293664 (The Pile)

Max Activating Token Index: 635

Text #19

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.8362. Min Act: -0.0000

Data Index: 297106 (The Pile)

Max Activating Token Index: 55