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

Dataset: The Pile

Neuron 945 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: 1.2338. Min Range: -1.2338

Max Act: 1.2338. Min Act: -0.0000

Data Index: 185057 (The Pile)

Max Activating Token Index: 703

Text #1

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.1243. Min Act: -0.0000

Data Index: 369355 (The Pile)

Max Activating Token Index: 365

Text #2

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.0917. Min Act: -0.0000

Data Index: 1926725 (The Pile)

Max Activating Token Index: 322

Text #3

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.0386. Min Act: -0.0000

Data Index: 1815137 (The Pile)

Max Activating Token Index: 416

Text #4

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.0881. Min Act: -0.0000

Data Index: 1407736 (The Pile)

Max Activating Token Index: 353

Text #5

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.0525. Min Act: -0.0000

Data Index: 764809 (The Pile)

Max Activating Token Index: 748

Text #6

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.0114. Min Act: -0.0000

Data Index: 263788 (The Pile)

Max Activating Token Index: 612

Text #7

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.0337. Min Act: -0.0000

Data Index: 1622347 (The Pile)

Max Activating Token Index: 844

Text #8

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.0590. Min Act: -0.0000

Data Index: 1682741 (The Pile)

Max Activating Token Index: 874

Text #9

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.0451. Min Act: -0.0000

Data Index: 208735 (The Pile)

Max Activating Token Index: 185

Text #10

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.0495. Min Act: -0.0000

Data Index: 1461511 (The Pile)

Max Activating Token Index: 834

Text #11

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.0229. Min Act: -0.0000

Data Index: 264158 (The Pile)

Max Activating Token Index: 264

Text #12

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.9897. Min Act: -0.0000

Data Index: 1165490 (The Pile)

Max Activating Token Index: 795

Text #13

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.0244. Min Act: -0.0000

Data Index: 1406275 (The Pile)

Max Activating Token Index: 238

Text #14

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.8835. Min Act: -0.0000

Data Index: 584761 (The Pile)

Max Activating Token Index: 923

Text #15

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.9821. Min Act: -0.0000

Data Index: 774233 (The Pile)

Max Activating Token Index: 316

Text #16

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.9181. Min Act: -0.0000

Data Index: 1435365 (The Pile)

Max Activating Token Index: 242

Text #17

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.8983. Min Act: -0.0000

Data Index: 572578 (The Pile)

Max Activating Token Index: 173

Text #18

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.9903. Min Act: -0.0000

Data Index: 1484871 (The Pile)

Max Activating Token Index: 123

Text #19

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.8656. Min Act: -0.0000

Data Index: 1352955 (The Pile)

Max Activating Token Index: 207