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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2784 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2385. Min Act: -0.0001

Data Index: 975020 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2243. Min Act: -0.0001

Data Index: 44709 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2321. Min Act: -0.0001

Data Index: 529467 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2366. Min Act: -0.0001

Data Index: 1129799 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2245. Min Act: -0.0001

Data Index: 421396 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2262. Min Act: -0.0001

Data Index: 253848 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2173. Min Act: -0.0001

Data Index: 1103885 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2241. Min Act: -0.0001

Data Index: 525500 (C4 (Web Text))

Max Activating Token Index: 413

Text #8

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2316. Min Act: -0.0001

Data Index: 96328 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2166. Min Act: -0.0001

Data Index: 513304 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2075. Min Act: -0.0001

Data Index: 798853 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2215. Min Act: -0.0001

Data Index: 10167 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2284. Min Act: -0.0001

Data Index: 1033923 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2188. Min Act: -0.0001

Data Index: 506588 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2121. Min Act: -0.0001

Data Index: 637955 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2120. Min Act: -0.0001

Data Index: 802437 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2191. Min Act: -0.0001

Data Index: 468547 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2086. Min Act: -0.0001

Data Index: 96631 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2153. Min Act: -0.0001

Data Index: 561204 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2142. Min Act: -0.0001

Data Index: 258184 (C4 (Web Text))

Max Activating Token Index: 394