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

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

Neuron 2296 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: 2.5777. Min Range: -2.5777

Max Act: 2.5777. Min Act: -0.0000

Data Index: 1554093 (Python Code)

Max Activating Token Index: 645

Text #1

Max Range: 2.5777. Min Range: -2.5777

Max Act: 2.0081. Min Act: -0.0000

Data Index: 1446195 (Python Code)

Max Activating Token Index: 507

Text #2

Max Range: 2.5777. Min Range: -2.5777

Max Act: 1.8346. Min Act: -0.0000

Data Index: 1572326 (Python Code)

Max Activating Token Index: 880

Text #3

Max Range: 2.5777. Min Range: -2.5777

Max Act: 1.6836. Min Act: -0.0000

Data Index: 1523334 (Python Code)

Max Activating Token Index: 673

Text #4

Max Range: 2.5777. Min Range: -2.5777

Max Act: 1.5239. Min Act: -0.0000

Data Index: 360241 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 2.5777. Min Range: -2.5777

Max Act: 1.6341. Min Act: -0.0000

Data Index: 1643262 (Python Code)

Max Activating Token Index: 130

Text #6

Max Range: 2.5777. Min Range: -2.5777

Max Act: 1.4918. Min Act: -0.0000

Data Index: 1609005 (Python Code)

Max Activating Token Index: 633

Text #7

Max Range: 2.5777. Min Range: -2.5777

Max Act: 1.6228. Min Act: -0.0000

Data Index: 1589663 (Python Code)

Max Activating Token Index: 518

Text #8

Max Range: 2.5777. Min Range: -2.5777

Max Act: 1.4460. Min Act: -0.0000

Data Index: 1446937 (Python Code)

Max Activating Token Index: 310

Text #9

Max Range: 2.5777. Min Range: -2.5777

Max Act: 1.4775. Min Act: -0.0000

Data Index: 1540116 (Python Code)

Max Activating Token Index: 251

Text #10

Max Range: 2.5777. Min Range: -2.5777

Max Act: 1.4198. Min Act: -0.0000

Data Index: 1617850 (Python Code)

Max Activating Token Index: 364

Text #11

Max Range: 2.5777. Min Range: -2.5777

Max Act: 1.4553. Min Act: -0.0000

Data Index: 1511048 (Python Code)

Max Activating Token Index: 530

Text #12

Max Range: 2.5777. Min Range: -2.5777

Max Act: 1.4615. Min Act: -0.0000

Data Index: 1554393 (Python Code)

Max Activating Token Index: 158

Text #13

Max Range: 2.5777. Min Range: -2.5777

Max Act: 1.4486. Min Act: -0.0000

Data Index: 1367420 (Python Code)

Max Activating Token Index: 715

Text #14

Max Range: 2.5777. Min Range: -2.5777

Max Act: 1.3758. Min Act: -0.0000

Data Index: 1522412 (Python Code)

Max Activating Token Index: 406

Text #15

Max Range: 2.5777. Min Range: -2.5777

Max Act: 1.4151. Min Act: -0.0000

Data Index: 175265 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 2.5777. Min Range: -2.5777

Max Act: 1.4597. Min Act: 0.0000

Data Index: 389320 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 2.5777. Min Range: -2.5777

Max Act: 1.6450. Min Act: -0.0000

Data Index: 1486754 (Python Code)

Max Activating Token Index: 1004

Text #18

Max Range: 2.5777. Min Range: -2.5777

Max Act: 1.3894. Min Act: -0.0000

Data Index: 1404615 (Python Code)

Max Activating Token Index: 954

Text #19

Max Range: 2.5777. Min Range: -2.5777

Max Act: 1.4536. Min Act: -0.0000

Data Index: 1606473 (Python Code)

Max Activating Token Index: 984