Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4104 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.9397. Min Range: -2.9397

Max Act: 2.9397. Min Act: -0.0000

Data Index: 1376153 (Python Code)

Max Activating Token Index: 198

Text #1

Max Range: 2.9397. Min Range: -2.9397

Max Act: 2.7938. Min Act: -0.0000

Data Index: 1511739 (Python Code)

Max Activating Token Index: 670

Text #2

Max Range: 2.9397. Min Range: -2.9397

Max Act: 2.8125. Min Act: -0.0000

Data Index: 1646486 (Python Code)

Max Activating Token Index: 887

Text #3

Max Range: 2.9397. Min Range: -2.9397

Max Act: 2.7737. Min Act: -0.0000

Data Index: 1444145 (Python Code)

Max Activating Token Index: 572

Text #4

Max Range: 2.9397. Min Range: -2.9397

Max Act: 2.5049. Min Act: -0.0000

Data Index: 1634365 (Python Code)

Max Activating Token Index: 695

Text #5

Max Range: 2.9397. Min Range: -2.9397

Max Act: 2.5753. Min Act: -0.0000

Data Index: 1647808 (Python Code)

Max Activating Token Index: 280

Text #6

Max Range: 2.9397. Min Range: -2.9397

Max Act: 2.4077. Min Act: -0.0000

Data Index: 1622095 (Python Code)

Max Activating Token Index: 293

Text #7

Max Range: 2.9397. Min Range: -2.9397

Max Act: 2.5582. Min Act: -0.0000

Data Index: 1618083 (Python Code)

Max Activating Token Index: 958

Text #8

Max Range: 2.9397. Min Range: -2.9397

Max Act: 2.5171. Min Act: -0.0000

Data Index: 1387773 (Python Code)

Max Activating Token Index: 764

Text #9

Max Range: 2.9397. Min Range: -2.9397

Max Act: 2.4704. Min Act: -0.0000

Data Index: 1631024 (Python Code)

Max Activating Token Index: 919

Text #10

Max Range: 2.9397. Min Range: -2.9397

Max Act: 2.4271. Min Act: -0.0000

Data Index: 1466428 (Python Code)

Max Activating Token Index: 6

Text #11

Max Range: 2.9397. Min Range: -2.9397

Max Act: 2.2407. Min Act: 0.0000

Data Index: 1644092 (Python Code)

Max Activating Token Index: 593

Text #12

Max Range: 2.9397. Min Range: -2.9397

Max Act: 2.2170. Min Act: 0.0000

Data Index: 1588435 (Python Code)

Max Activating Token Index: 480

Text #13

Max Range: 2.9397. Min Range: -2.9397

Max Act: 2.3530. Min Act: 0.0000

Data Index: 1637737 (Python Code)

Max Activating Token Index: 472

Text #14

Max Range: 2.9397. Min Range: -2.9397

Max Act: 2.1910. Min Act: -0.0000

Data Index: 1590931 (Python Code)

Max Activating Token Index: 925

Text #15

Max Range: 2.9397. Min Range: -2.9397

Max Act: 2.4187. Min Act: -0.0000

Data Index: 1617827 (Python Code)

Max Activating Token Index: 764

Text #16

Max Range: 2.9397. Min Range: -2.9397

Max Act: 2.1940. Min Act: 0.0000

Data Index: 1403544 (Python Code)

Max Activating Token Index: 322

Text #17

Max Range: 2.9397. Min Range: -2.9397

Max Act: 2.4521. Min Act: -0.0000

Data Index: 1397042 (Python Code)

Max Activating Token Index: 279

Text #18

Max Range: 2.9397. Min Range: -2.9397

Max Act: 2.1576. Min Act: -0.0000

Data Index: 1567411 (Python Code)

Max Activating Token Index: 917

Text #19

Max Range: 2.9397. Min Range: -2.9397

Max Act: 2.2962. Min Act: -0.0000

Data Index: 1512091 (Python Code)

Max Activating Token Index: 946