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

Dataset: The Pile

Neuron 2403 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: 1.6254. Min Range: -1.6254

Max Act: 1.6254. Min Act: -0.0000

Data Index: 1616881 (The Pile)

Max Activating Token Index: 877

Text #1

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.6079. Min Act: -0.0000

Data Index: 37289 (The Pile)

Max Activating Token Index: 440

Text #2

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.5227. Min Act: -0.0000

Data Index: 1914596 (The Pile)

Max Activating Token Index: 346

Text #3

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.5326. Min Act: -0.0000

Data Index: 1625494 (The Pile)

Max Activating Token Index: 815

Text #4

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.5002. Min Act: -0.0000

Data Index: 475645 (The Pile)

Max Activating Token Index: 221

Text #5

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.4818. Min Act: -0.0000

Data Index: 1787940 (The Pile)

Max Activating Token Index: 950

Text #6

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.3237. Min Act: -0.0000

Data Index: 800176 (The Pile)

Max Activating Token Index: 830

Text #7

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.3981. Min Act: -0.0000

Data Index: 331936 (The Pile)

Max Activating Token Index: 619

Text #8

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.3721. Min Act: -0.0000

Data Index: 576267 (The Pile)

Max Activating Token Index: 321

Text #9

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.3652. Min Act: -0.0000

Data Index: 912323 (The Pile)

Max Activating Token Index: 914

Text #10

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.3457. Min Act: -0.0000

Data Index: 856031 (The Pile)

Max Activating Token Index: 293

Text #11

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.4254. Min Act: -0.0000

Data Index: 86022 (The Pile)

Max Activating Token Index: 390

Text #12

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.3416. Min Act: -0.0000

Data Index: 1035132 (The Pile)

Max Activating Token Index: 280

Text #13

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.3346. Min Act: -0.0000

Data Index: 215407 (The Pile)

Max Activating Token Index: 913

Text #14

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.1761. Min Act: -0.0000

Data Index: 718777 (The Pile)

Max Activating Token Index: 333

Text #15

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.2190. Min Act: -0.0000

Data Index: 383005 (The Pile)

Max Activating Token Index: 636

Text #16

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.2688. Min Act: -0.0000

Data Index: 1366130 (The Pile)

Max Activating Token Index: 464

Text #17

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.1870. Min Act: -0.0000

Data Index: 1831502 (The Pile)

Max Activating Token Index: 435

Text #18

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.3018. Min Act: -0.0000

Data Index: 1898182 (The Pile)

Max Activating Token Index: 613

Text #19

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.3170. Min Act: -0.0000

Data Index: 1970613 (The Pile)

Max Activating Token Index: 933