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

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

Neuron 1675 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2636. Min Range: -1.2636

Max Act: 1.2636. Min Act: -0.0000

Data Index: 1513127 (Python Code)

Max Activating Token Index: 968

Text #1

Max Range: 1.2636. Min Range: -1.2636

Max Act: 1.1017. Min Act: -0.0000

Data Index: 1489925 (Python Code)

Max Activating Token Index: 245

Text #2

Max Range: 1.2636. Min Range: -1.2636

Max Act: 1.1312. Min Act: -0.0000

Data Index: 1431795 (Python Code)

Max Activating Token Index: 492

Text #3

Max Range: 1.2636. Min Range: -1.2636

Max Act: 1.0923. Min Act: -0.0000

Data Index: 1493129 (Python Code)

Max Activating Token Index: 200

Text #4

Max Range: 1.2636. Min Range: -1.2636

Max Act: 1.0970. Min Act: -0.0000

Data Index: 525002 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 1.2636. Min Range: -1.2636

Max Act: 1.0520. Min Act: -0.0000

Data Index: 1366127 (Python Code)

Max Activating Token Index: 330

Text #6

Max Range: 1.2636. Min Range: -1.2636

Max Act: 1.0723. Min Act: -0.0000

Data Index: 468500 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 1.2636. Min Range: -1.2636

Max Act: 0.9888. Min Act: -0.0000

Data Index: 1435640 (Python Code)

Max Activating Token Index: 188

Text #8

Max Range: 1.2636. Min Range: -1.2636

Max Act: 1.0832. Min Act: -0.0001

Data Index: 1064456 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 1.2636. Min Range: -1.2636

Max Act: 1.0186. Min Act: -0.0000

Data Index: 1536091 (Python Code)

Max Activating Token Index: 75

Text #10

Max Range: 1.2636. Min Range: -1.2636

Max Act: 1.0453. Min Act: -0.0000

Data Index: 1573647 (Python Code)

Max Activating Token Index: 708

Text #11

Max Range: 1.2636. Min Range: -1.2636

Max Act: 1.0712. Min Act: -0.0000

Data Index: 1594808 (Python Code)

Max Activating Token Index: 644

Text #12

Max Range: 1.2636. Min Range: -1.2636

Max Act: 1.0340. Min Act: -0.0001

Data Index: 1171024 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 1.2636. Min Range: -1.2636

Max Act: 1.0333. Min Act: -0.0001

Data Index: 1449576 (Python Code)

Max Activating Token Index: 662

Text #14

Max Range: 1.2636. Min Range: -1.2636

Max Act: 0.9281. Min Act: -0.0000

Data Index: 1582519 (Python Code)

Max Activating Token Index: 542

Text #15

Max Range: 1.2636. Min Range: -1.2636

Max Act: 1.0206. Min Act: -0.0000

Data Index: 1463451 (Python Code)

Max Activating Token Index: 426

Text #16

Max Range: 1.2636. Min Range: -1.2636

Max Act: 0.9155. Min Act: -0.0000

Data Index: 1539676 (Python Code)

Max Activating Token Index: 210

Text #17

Max Range: 1.2636. Min Range: -1.2636

Max Act: 0.9224. Min Act: -0.0001

Data Index: 1444010 (Python Code)

Max Activating Token Index: 1011

Text #18

Max Range: 1.2636. Min Range: -1.2636

Max Act: 0.9307. Min Act: -0.0000

Data Index: 1478210 (Python Code)

Max Activating Token Index: 847

Text #19

Max Range: 1.2636. Min Range: -1.2636

Max Act: 0.9879. Min Act: -0.0000

Data Index: 1384666 (Python Code)

Max Activating Token Index: 459