Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 360 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6293. Min Range: -0.6293

Max Act: 0.6293. Min Act: -0.0000

Data Index: 424302 (The Pile)

Max Activating Token Index: 316

Text #1

Max Range: 0.6293. Min Range: -0.6293

Max Act: 0.5994. Min Act: -0.0000

Data Index: 1860564 (The Pile)

Max Activating Token Index: 552

Text #2

Max Range: 0.6293. Min Range: -0.6293

Max Act: 0.5841. Min Act: -0.0000

Data Index: 440240 (The Pile)

Max Activating Token Index: 73

Text #3

Max Range: 0.6293. Min Range: -0.6293

Max Act: 0.5660. Min Act: -0.0000

Data Index: 701581 (The Pile)

Max Activating Token Index: 716

Text #4

Max Range: 0.6293. Min Range: -0.6293

Max Act: 0.5467. Min Act: -0.0000

Data Index: 692257 (The Pile)

Max Activating Token Index: 252

Text #5

Max Range: 0.6293. Min Range: -0.6293

Max Act: 0.5611. Min Act: -0.0000

Data Index: 1119541 (The Pile)

Max Activating Token Index: 236

Text #6

Max Range: 0.6293. Min Range: -0.6293

Max Act: 0.5600. Min Act: -0.0000

Data Index: 1414343 (The Pile)

Max Activating Token Index: 386

Text #7

Max Range: 0.6293. Min Range: -0.6293

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1844046 (The Pile)

Max Activating Token Index: 141

Text #8

Max Range: 0.6293. Min Range: -0.6293

Max Act: 0.5597. Min Act: -0.0000

Data Index: 296817 (The Pile)

Max Activating Token Index: 369

Text #9

Max Range: 0.6293. Min Range: -0.6293

Max Act: 0.5409. Min Act: -0.0000

Data Index: 548217 (The Pile)

Max Activating Token Index: 22

Text #10

Max Range: 0.6293. Min Range: -0.6293

Max Act: 0.5445. Min Act: -0.0000

Data Index: 767828 (The Pile)

Max Activating Token Index: 612

Text #11

Max Range: 0.6293. Min Range: -0.6293

Max Act: 0.5365. Min Act: -0.0000

Data Index: 1154595 (The Pile)

Max Activating Token Index: 540

Text #12

Max Range: 0.6293. Min Range: -0.6293

Max Act: 0.5666. Min Act: -0.0000

Data Index: 621231 (The Pile)

Max Activating Token Index: 162

Text #13

Max Range: 0.6293. Min Range: -0.6293

Max Act: 0.5241. Min Act: -0.0000

Data Index: 1398135 (The Pile)

Max Activating Token Index: 325

Text #14

Max Range: 0.6293. Min Range: -0.6293

Max Act: 0.5368. Min Act: -0.0000

Data Index: 223711 (The Pile)

Max Activating Token Index: 244

Text #15

Max Range: 0.6293. Min Range: -0.6293

Max Act: 0.5128. Min Act: -0.0000

Data Index: 313454 (The Pile)

Max Activating Token Index: 232

Text #16

Max Range: 0.6293. Min Range: -0.6293

Max Act: 0.5139. Min Act: -0.0000

Data Index: 846059 (The Pile)

Max Activating Token Index: 666

Text #17

Max Range: 0.6293. Min Range: -0.6293

Max Act: 0.5232. Min Act: -0.0000

Data Index: 1433067 (The Pile)

Max Activating Token Index: 175

Text #18

Max Range: 0.6293. Min Range: -0.6293

Max Act: 0.5394. Min Act: -0.0000

Data Index: 1278432 (The Pile)

Max Activating Token Index: 982

Text #19

Max Range: 0.6293. Min Range: -0.6293

Max Act: 0.5026. Min Act: -0.0000

Data Index: 769095 (The Pile)

Max Activating Token Index: 764