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

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

Neuron 432 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9964. Min Range: -4.9964

Max Act: 4.9964. Min Act: -0.0000

Data Index: 1432867 (Python Code)

Max Activating Token Index: 237

Text #1

Max Range: 4.9964. Min Range: -4.9964

Max Act: 4.1257. Min Act: -0.0001

Data Index: 1446280 (Python Code)

Max Activating Token Index: 867

Text #2

Max Range: 4.9964. Min Range: -4.9964

Max Act: 4.3492. Min Act: -0.0000

Data Index: 1408169 (Python Code)

Max Activating Token Index: 1006

Text #3

Max Range: 4.9964. Min Range: -4.9964

Max Act: 4.4932. Min Act: -0.0001

Data Index: 1387424 (Python Code)

Max Activating Token Index: 990

Text #4

Max Range: 4.9964. Min Range: -4.9964

Max Act: 4.2862. Min Act: -0.0000

Data Index: 590067 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 4.9964. Min Range: -4.9964

Max Act: 4.2056. Min Act: -0.0000

Data Index: 1560690 (Python Code)

Max Activating Token Index: 718

Text #6

Max Range: 4.9964. Min Range: -4.9964

Max Act: 4.3145. Min Act: -0.0000

Data Index: 1367134 (Python Code)

Max Activating Token Index: 297

Text #7

Max Range: 4.9964. Min Range: -4.9964

Max Act: 3.9591. Min Act: -0.0001

Data Index: 1469979 (Python Code)

Max Activating Token Index: 406

Text #8

Max Range: 4.9964. Min Range: -4.9964

Max Act: 4.1920. Min Act: -0.0001

Data Index: 1646066 (Python Code)

Max Activating Token Index: 416

Text #9

Max Range: 4.9964. Min Range: -4.9964

Max Act: 4.2154. Min Act: -0.0001

Data Index: 1635847 (Python Code)

Max Activating Token Index: 665

Text #10

Max Range: 4.9964. Min Range: -4.9964

Max Act: 4.0258. Min Act: -0.0000

Data Index: 973613 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 4.9964. Min Range: -4.9964

Max Act: 4.2058. Min Act: -0.0001

Data Index: 1429839 (Python Code)

Max Activating Token Index: 889

Text #12

Max Range: 4.9964. Min Range: -4.9964

Max Act: 4.3198. Min Act: -0.0000

Data Index: 1379522 (Python Code)

Max Activating Token Index: 278

Text #13

Max Range: 4.9964. Min Range: -4.9964

Max Act: 4.0338. Min Act: -0.0001

Data Index: 1560626 (Python Code)

Max Activating Token Index: 838

Text #14

Max Range: 4.9964. Min Range: -4.9964

Max Act: 3.9436. Min Act: -0.0000

Data Index: 1421564 (Python Code)

Max Activating Token Index: 590

Text #15

Max Range: 4.9964. Min Range: -4.9964

Max Act: 4.2922. Min Act: -0.0000

Data Index: 1496731 (Python Code)

Max Activating Token Index: 934

Text #16

Max Range: 4.9964. Min Range: -4.9964

Max Act: 3.9903. Min Act: -0.0001

Data Index: 1603448 (Python Code)

Max Activating Token Index: 608

Text #17

Max Range: 4.9964. Min Range: -4.9964

Max Act: 4.2602. Min Act: -0.0000

Data Index: 1609491 (Python Code)

Max Activating Token Index: 339

Text #18

Max Range: 4.9964. Min Range: -4.9964

Max Act: 4.1068. Min Act: -0.0000

Data Index: 1426679 (Python Code)

Max Activating Token Index: 318

Text #19

Max Range: 4.9964. Min Range: -4.9964

Max Act: 3.9354. Min Act: -0.0001

Data Index: 1649731 (Python Code)

Max Activating Token Index: 956