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

Dataset: The Pile

Neuron 2134 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: 3.4538. Min Range: -3.4538

Max Act: 3.4538. Min Act: -0.0000

Data Index: 197109 (The Pile)

Max Activating Token Index: 190

Text #1

Max Range: 3.4538. Min Range: -3.4538

Max Act: 3.4163. Min Act: -0.0000

Data Index: 211504 (The Pile)

Max Activating Token Index: 137

Text #2

Max Range: 3.4538. Min Range: -3.4538

Max Act: 3.2310. Min Act: -0.0000

Data Index: 126295 (The Pile)

Max Activating Token Index: 145

Text #3

Max Range: 3.4538. Min Range: -3.4538

Max Act: 3.2248. Min Act: -0.0000

Data Index: 873316 (The Pile)

Max Activating Token Index: 444

Text #4

Max Range: 3.4538. Min Range: -3.4538

Max Act: 3.2961. Min Act: -0.0000

Data Index: 906328 (The Pile)

Max Activating Token Index: 617

Text #5

Max Range: 3.4538. Min Range: -3.4538

Max Act: 3.1460. Min Act: -0.0000

Data Index: 906736 (The Pile)

Max Activating Token Index: 798

Text #6

Max Range: 3.4538. Min Range: -3.4538

Max Act: 3.1334. Min Act: -0.0000

Data Index: 167682 (The Pile)

Max Activating Token Index: 92

Text #7

Max Range: 3.4538. Min Range: -3.4538

Max Act: 2.9503. Min Act: -0.0000

Data Index: 415013 (The Pile)

Max Activating Token Index: 120

Text #8

Max Range: 3.4538. Min Range: -3.4538

Max Act: 3.0311. Min Act: -0.0000

Data Index: 170391 (The Pile)

Max Activating Token Index: 449

Text #9

Max Range: 3.4538. Min Range: -3.4538

Max Act: 3.0301. Min Act: -0.0000

Data Index: 1279757 (The Pile)

Max Activating Token Index: 311

Text #10

Max Range: 3.4538. Min Range: -3.4538

Max Act: 2.8691. Min Act: -0.0000

Data Index: 937823 (The Pile)

Max Activating Token Index: 492

Text #11

Max Range: 3.4538. Min Range: -3.4538

Max Act: 2.9102. Min Act: -0.0000

Data Index: 1781508 (The Pile)

Max Activating Token Index: 172

Text #12

Max Range: 3.4538. Min Range: -3.4538

Max Act: 3.0012. Min Act: -0.0000

Data Index: 980916 (The Pile)

Max Activating Token Index: 497

Text #13

Max Range: 3.4538. Min Range: -3.4538

Max Act: 2.7892. Min Act: -0.0000

Data Index: 1811000 (The Pile)

Max Activating Token Index: 657

Text #14

Max Range: 3.4538. Min Range: -3.4538

Max Act: 2.7814. Min Act: -0.0000

Data Index: 1987870 (The Pile)

Max Activating Token Index: 832

Text #15

Max Range: 3.4538. Min Range: -3.4538

Max Act: 2.7876. Min Act: -0.0000

Data Index: 1456006 (The Pile)

Max Activating Token Index: 353

Text #16

Max Range: 3.4538. Min Range: -3.4538

Max Act: 2.6232. Min Act: -0.0000

Data Index: 681133 (The Pile)

Max Activating Token Index: 666

Text #17

Max Range: 3.4538. Min Range: -3.4538

Max Act: 2.8884. Min Act: -0.0000

Data Index: 584170 (The Pile)

Max Activating Token Index: 394

Text #18

Max Range: 3.4538. Min Range: -3.4538

Max Act: 2.7600. Min Act: -0.0000

Data Index: 884714 (The Pile)

Max Activating Token Index: 12

Text #19

Max Range: 3.4538. Min Range: -3.4538

Max Act: 2.8372. Min Act: -0.0000

Data Index: 671374 (The Pile)

Max Activating Token Index: 124