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

Dataset: The Pile

Neuron 1049 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5271. Min Range: -1.5271

Max Act: 1.4659. Min Act: -0.0000

Data Index: 437294 (The Pile)

Max Activating Token Index: 410

Text #1

Max Range: 1.5271. Min Range: -1.5271

Max Act: 1.5271. Min Act: -0.0000

Data Index: 98641 (The Pile)

Max Activating Token Index: 561

Text #2

Max Range: 1.5271. Min Range: -1.5271

Max Act: 1.5068. Min Act: -0.0000

Data Index: 1320253 (The Pile)

Max Activating Token Index: 506

Text #3

Max Range: 1.5271. Min Range: -1.5271

Max Act: 1.3803. Min Act: -0.0000

Data Index: 1658545 (The Pile)

Max Activating Token Index: 791

Text #4

Max Range: 1.5271. Min Range: -1.5271

Max Act: 1.4376. Min Act: -0.0000

Data Index: 1831603 (The Pile)

Max Activating Token Index: 459

Text #5

Max Range: 1.5271. Min Range: -1.5271

Max Act: 1.4205. Min Act: -0.0000

Data Index: 1461828 (The Pile)

Max Activating Token Index: 264

Text #6

Max Range: 1.5271. Min Range: -1.5271

Max Act: 1.3095. Min Act: -0.0000

Data Index: 596446 (The Pile)

Max Activating Token Index: 249

Text #7

Max Range: 1.5271. Min Range: -1.5271

Max Act: 1.3369. Min Act: -0.0000

Data Index: 1244887 (The Pile)

Max Activating Token Index: 395

Text #8

Max Range: 1.5271. Min Range: -1.5271

Max Act: 1.3520. Min Act: -0.0000

Data Index: 1860250 (The Pile)

Max Activating Token Index: 81

Text #9

Max Range: 1.5271. Min Range: -1.5271

Max Act: 1.3397. Min Act: -0.0000

Data Index: 1742730 (The Pile)

Max Activating Token Index: 404

Text #10

Max Range: 1.5271. Min Range: -1.5271

Max Act: 1.2963. Min Act: -0.0000

Data Index: 362776 (The Pile)

Max Activating Token Index: 293

Text #11

Max Range: 1.5271. Min Range: -1.5271

Max Act: 1.2573. Min Act: -0.0000

Data Index: 1859677 (The Pile)

Max Activating Token Index: 386

Text #12

Max Range: 1.5271. Min Range: -1.5271

Max Act: 1.2754. Min Act: -0.0000

Data Index: 970254 (The Pile)

Max Activating Token Index: 179

Text #13

Max Range: 1.5271. Min Range: -1.5271

Max Act: 1.3359. Min Act: -0.0000

Data Index: 410990 (The Pile)

Max Activating Token Index: 998

Text #14

Max Range: 1.5271. Min Range: -1.5271

Max Act: 1.1893. Min Act: -0.0000

Data Index: 1150930 (The Pile)

Max Activating Token Index: 122

Text #15

Max Range: 1.5271. Min Range: -1.5271

Max Act: 1.2161. Min Act: -0.0000

Data Index: 895104 (The Pile)

Max Activating Token Index: 255

Text #16

Max Range: 1.5271. Min Range: -1.5271

Max Act: 1.2487. Min Act: -0.0000

Data Index: 1031217 (The Pile)

Max Activating Token Index: 163

Text #17

Max Range: 1.5271. Min Range: -1.5271

Max Act: 1.1436. Min Act: -0.0000

Data Index: 1213340 (The Pile)

Max Activating Token Index: 135

Text #18

Max Range: 1.5271. Min Range: -1.5271

Max Act: 1.2389. Min Act: -0.0000

Data Index: 679313 (The Pile)

Max Activating Token Index: 325

Text #19

Max Range: 1.5271. Min Range: -1.5271

Max Act: 1.2126. Min Act: -0.0000

Data Index: 1648731 (The Pile)

Max Activating Token Index: 232