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

Dataset: The Pile

Neuron 1935 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: 3.5058. Min Range: -3.5058

Max Act: 3.5058. Min Act: -0.0000

Data Index: 273139 (The Pile)

Max Activating Token Index: 157

Text #1

Max Range: 3.5058. Min Range: -3.5058

Max Act: 2.9440. Min Act: -0.0000

Data Index: 416018 (The Pile)

Max Activating Token Index: 187

Text #2

Max Range: 3.5058. Min Range: -3.5058

Max Act: 2.5506. Min Act: -0.0000

Data Index: 873274 (The Pile)

Max Activating Token Index: 385

Text #3

Max Range: 3.5058. Min Range: -3.5058

Max Act: 2.4368. Min Act: -0.0000

Data Index: 470434 (The Pile)

Max Activating Token Index: 398

Text #4

Max Range: 3.5058. Min Range: -3.5058

Max Act: 2.4432. Min Act: -0.0000

Data Index: 199557 (The Pile)

Max Activating Token Index: 220

Text #5

Max Range: 3.5058. Min Range: -3.5058

Max Act: 2.4487. Min Act: -0.0000

Data Index: 1624301 (The Pile)

Max Activating Token Index: 165

Text #6

Max Range: 3.5058. Min Range: -3.5058

Max Act: 2.3751. Min Act: -0.0000

Data Index: 383205 (The Pile)

Max Activating Token Index: 385

Text #7

Max Range: 3.5058. Min Range: -3.5058

Max Act: 2.3423. Min Act: -0.0000

Data Index: 1340421 (The Pile)

Max Activating Token Index: 521

Text #8

Max Range: 3.5058. Min Range: -3.5058

Max Act: 2.1604. Min Act: -0.0000

Data Index: 231109 (The Pile)

Max Activating Token Index: 723

Text #9

Max Range: 3.5058. Min Range: -3.5058

Max Act: 2.2274. Min Act: -0.0000

Data Index: 38601 (The Pile)

Max Activating Token Index: 157

Text #10

Max Range: 3.5058. Min Range: -3.5058

Max Act: 2.2472. Min Act: -0.0000

Data Index: 1108925 (The Pile)

Max Activating Token Index: 318

Text #11

Max Range: 3.5058. Min Range: -3.5058

Max Act: 2.1858. Min Act: -0.0000

Data Index: 488362 (The Pile)

Max Activating Token Index: 528

Text #12

Max Range: 3.5058. Min Range: -3.5058

Max Act: 2.1842. Min Act: -0.0000

Data Index: 536069 (The Pile)

Max Activating Token Index: 401

Text #13

Max Range: 3.5058. Min Range: -3.5058

Max Act: 2.0709. Min Act: 0.0000

Data Index: 1014504 (The Pile)

Max Activating Token Index: 313

Text #14

Max Range: 3.5058. Min Range: -3.5058

Max Act: 2.0603. Min Act: -0.0000

Data Index: 328339 (The Pile)

Max Activating Token Index: 403

Text #15

Max Range: 3.5058. Min Range: -3.5058

Max Act: 2.2107. Min Act: -0.0000

Data Index: 520947 (The Pile)

Max Activating Token Index: 760

Text #16

Max Range: 3.5058. Min Range: -3.5058

Max Act: 2.0131. Min Act: -0.0000

Data Index: 136274 (The Pile)

Max Activating Token Index: 201

Text #17

Max Range: 3.5058. Min Range: -3.5058

Max Act: 2.2251. Min Act: -0.0000

Data Index: 800331 (The Pile)

Max Activating Token Index: 832

Text #18

Max Range: 3.5058. Min Range: -3.5058

Max Act: 2.0008. Min Act: -0.0000

Data Index: 1779299 (The Pile)

Max Activating Token Index: 538

Text #19

Max Range: 3.5058. Min Range: -3.5058

Max Act: 2.3204. Min Act: -0.0000

Data Index: 334378 (The Pile)

Max Activating Token Index: 254