Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 431 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2519. Min Act: -0.0001

Data Index: 1376000 (Python Code)

Max Activating Token Index: 567

Text #1

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2487. Min Act: -0.0001

Data Index: 1632941 (Python Code)

Max Activating Token Index: 509

Text #2

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2399. Min Act: -0.0001

Data Index: 1636278 (Python Code)

Max Activating Token Index: 895

Text #3

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2524. Min Act: -0.0001

Data Index: 1587571 (Python Code)

Max Activating Token Index: 763

Text #4

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2264. Min Act: -0.0001

Data Index: 1583567 (Python Code)

Max Activating Token Index: 414

Text #5

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2235. Min Act: -0.0001

Data Index: 1459750 (Python Code)

Max Activating Token Index: 797

Text #6

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2143. Min Act: -0.0001

Data Index: 1444764 (Python Code)

Max Activating Token Index: 488

Text #7

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2343. Min Act: -0.0001

Data Index: 1652085 (Python Code)

Max Activating Token Index: 726

Text #8

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2255. Min Act: -0.0001

Data Index: 1410227 (Python Code)

Max Activating Token Index: 567

Text #9

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2167. Min Act: -0.0001

Data Index: 1392704 (Python Code)

Max Activating Token Index: 654

Text #10

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2091. Min Act: -0.0001

Data Index: 1625346 (Python Code)

Max Activating Token Index: 565

Text #11

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2282. Min Act: -0.0001

Data Index: 1622735 (Python Code)

Max Activating Token Index: 78

Text #12

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2155. Min Act: -0.0001

Data Index: 1484821 (Python Code)

Max Activating Token Index: 32

Text #13

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2133. Min Act: -0.0001

Data Index: 1136846 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2132. Min Act: -0.0001

Data Index: 1476277 (Python Code)

Max Activating Token Index: 953

Text #15

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2178. Min Act: -0.0001

Data Index: 1544752 (Python Code)

Max Activating Token Index: 731

Text #16

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2108. Min Act: -0.0001

Data Index: 1309779 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2000. Min Act: -0.0001

Data Index: 1361830 (Python Code)

Max Activating Token Index: 270

Text #18

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2109. Min Act: -0.0001

Data Index: 1435934 (Python Code)

Max Activating Token Index: 141

Text #19

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2071. Min Act: -0.0001

Data Index: 1421784 (Python Code)

Max Activating Token Index: 414