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

Dataset: The Pile

Neuron 3383 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: 1.2244. Min Range: -1.2244

Max Act: 1.2244. Min Act: -0.0000

Data Index: 1453322 (The Pile)

Max Activating Token Index: 790

Text #1

Max Range: 1.2244. Min Range: -1.2244

Max Act: 1.1304. Min Act: -0.0000

Data Index: 1237029 (The Pile)

Max Activating Token Index: 112

Text #2

Max Range: 1.2244. Min Range: -1.2244

Max Act: 1.0719. Min Act: -0.0000

Data Index: 851120 (The Pile)

Max Activating Token Index: 425

Text #3

Max Range: 1.2244. Min Range: -1.2244

Max Act: 0.9741. Min Act: -0.0000

Data Index: 1012128 (The Pile)

Max Activating Token Index: 873

Text #4

Max Range: 1.2244. Min Range: -1.2244

Max Act: 0.9797. Min Act: -0.0000

Data Index: 410561 (The Pile)

Max Activating Token Index: 362

Text #5

Max Range: 1.2244. Min Range: -1.2244

Max Act: 0.9400. Min Act: -0.0000

Data Index: 1909149 (The Pile)

Max Activating Token Index: 245

Text #6

Max Range: 1.2244. Min Range: -1.2244

Max Act: 0.9264. Min Act: -0.0000

Data Index: 252323 (The Pile)

Max Activating Token Index: 11

Text #7

Max Range: 1.2244. Min Range: -1.2244

Max Act: 0.9219. Min Act: -0.0000

Data Index: 148798 (The Pile)

Max Activating Token Index: 296

Text #8

Max Range: 1.2244. Min Range: -1.2244

Max Act: 0.8650. Min Act: -0.0000

Data Index: 505014 (The Pile)

Max Activating Token Index: 886

Text #9

Max Range: 1.2244. Min Range: -1.2244

Max Act: 0.8378. Min Act: -0.0000

Data Index: 482340 (The Pile)

Max Activating Token Index: 591

Text #10

Max Range: 1.2244. Min Range: -1.2244

Max Act: 0.8838. Min Act: -0.0000

Data Index: 1260863 (The Pile)

Max Activating Token Index: 326

Text #11

Max Range: 1.2244. Min Range: -1.2244

Max Act: 0.9382. Min Act: -0.0000

Data Index: 1079164 (The Pile)

Max Activating Token Index: 891

Text #12

Max Range: 1.2244. Min Range: -1.2244

Max Act: 0.8183. Min Act: -0.0000

Data Index: 268704 (The Pile)

Max Activating Token Index: 336

Text #13

Max Range: 1.2244. Min Range: -1.2244

Max Act: 0.8286. Min Act: -0.0000

Data Index: 506858 (The Pile)

Max Activating Token Index: 730

Text #14

Max Range: 1.2244. Min Range: -1.2244

Max Act: 0.8285. Min Act: -0.0000

Data Index: 1212056 (The Pile)

Max Activating Token Index: 905

Text #15

Max Range: 1.2244. Min Range: -1.2244

Max Act: 0.7706. Min Act: -0.0000

Data Index: 1213202 (The Pile)

Max Activating Token Index: 158

Text #16

Max Range: 1.2244. Min Range: -1.2244

Max Act: 0.7459. Min Act: -0.0000

Data Index: 1298295 (The Pile)

Max Activating Token Index: 424

Text #17

Max Range: 1.2244. Min Range: -1.2244

Max Act: 0.8067. Min Act: -0.0000

Data Index: 1981467 (The Pile)

Max Activating Token Index: 670

Text #18

Max Range: 1.2244. Min Range: -1.2244

Max Act: 0.7718. Min Act: -0.0000

Data Index: 1376386 (The Pile)

Max Activating Token Index: 441

Text #19

Max Range: 1.2244. Min Range: -1.2244

Max Act: 0.6655. Min Act: -0.0000

Data Index: 260531 (The Pile)

Max Activating Token Index: 819