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

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

Neuron 3404 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: 1.5372. Min Range: -1.5372

Max Act: 1.5372. Min Act: -0.0000

Data Index: 1616352 (Python Code)

Max Activating Token Index: 60

Text #1

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.3120. Min Act: -0.0000

Data Index: 1643583 (Python Code)

Max Activating Token Index: 899

Text #2

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.3045. Min Act: -0.0001

Data Index: 1414196 (Python Code)

Max Activating Token Index: 237

Text #3

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.2851. Min Act: -0.0000

Data Index: 1593446 (Python Code)

Max Activating Token Index: 1011

Text #4

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.2581. Min Act: -0.0000

Data Index: 1647865 (Python Code)

Max Activating Token Index: 532

Text #5

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.1378. Min Act: -0.0000

Data Index: 1445960 (Python Code)

Max Activating Token Index: 476

Text #6

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.0842. Min Act: -0.0000

Data Index: 1648310 (Python Code)

Max Activating Token Index: 324

Text #7

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.0937. Min Act: -0.0001

Data Index: 1367635 (Python Code)

Max Activating Token Index: 585

Text #8

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.1057. Min Act: -0.0001

Data Index: 1368499 (Python Code)

Max Activating Token Index: 971

Text #9

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.0913. Min Act: -0.0000

Data Index: 1511653 (Python Code)

Max Activating Token Index: 216

Text #10

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.0652. Min Act: -0.0001

Data Index: 1610457 (Python Code)

Max Activating Token Index: 512

Text #11

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.0564. Min Act: -0.0000

Data Index: 1603752 (Python Code)

Max Activating Token Index: 693

Text #12

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.0128. Min Act: -0.0000

Data Index: 1605988 (Python Code)

Max Activating Token Index: 79

Text #13

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.9346. Min Act: -0.0000

Data Index: 1379702 (Python Code)

Max Activating Token Index: 868

Text #14

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.0428. Min Act: -0.0000

Data Index: 1570631 (Python Code)

Max Activating Token Index: 618

Text #15

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.0135. Min Act: -0.0000

Data Index: 1410562 (Python Code)

Max Activating Token Index: 815

Text #16

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.9699. Min Act: -0.0000

Data Index: 1647587 (Python Code)

Max Activating Token Index: 309

Text #17

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.9972. Min Act: -0.0001

Data Index: 1427246 (Python Code)

Max Activating Token Index: 125

Text #18

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.9543. Min Act: -0.0000

Data Index: 1419878 (Python Code)

Max Activating Token Index: 553

Text #19

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.9600. Min Act: -0.0000

Data Index: 1497427 (Python Code)

Max Activating Token Index: 359