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

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

Neuron 3627 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: 2.1696. Min Range: -2.1696

Max Act: 2.1696. Min Act: -0.0000

Data Index: 1448416 (Python Code)

Max Activating Token Index: 886

Text #1

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.8422. Min Act: -0.0000

Data Index: 1558333 (Python Code)

Max Activating Token Index: 613

Text #2

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.6367. Min Act: -0.0000

Data Index: 1436616 (Python Code)

Max Activating Token Index: 1009

Text #3

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.5603. Min Act: -0.0000

Data Index: 1603719 (Python Code)

Max Activating Token Index: 805

Text #4

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.5403. Min Act: -0.0000

Data Index: 1416662 (Python Code)

Max Activating Token Index: 873

Text #5

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.8402. Min Act: -0.0000

Data Index: 1558529 (Python Code)

Max Activating Token Index: 813

Text #6

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.5595. Min Act: -0.0000

Data Index: 993419 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.7122. Min Act: -0.0000

Data Index: 1498169 (Python Code)

Max Activating Token Index: 631

Text #8

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.7408. Min Act: -0.0000

Data Index: 1631322 (Python Code)

Max Activating Token Index: 585

Text #9

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.7080. Min Act: -0.0000

Data Index: 1655809 (Python Code)

Max Activating Token Index: 984

Text #10

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.7495. Min Act: -0.0000

Data Index: 1645508 (Python Code)

Max Activating Token Index: 918

Text #11

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.5754. Min Act: -0.0000

Data Index: 1612605 (Python Code)

Max Activating Token Index: 902

Text #12

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.6053. Min Act: -0.0000

Data Index: 268449 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.6429. Min Act: -0.0000

Data Index: 1421818 (Python Code)

Max Activating Token Index: 593

Text #14

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.5762. Min Act: -0.0000

Data Index: 1361454 (Python Code)

Max Activating Token Index: 204

Text #15

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.5669. Min Act: -0.0000

Data Index: 858283 (C4 (Web Text))

Max Activating Token Index: 415

Text #16

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.5966. Min Act: -0.0000

Data Index: 1419139 (Python Code)

Max Activating Token Index: 346

Text #17

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.5028. Min Act: -0.0000

Data Index: 1429488 (Python Code)

Max Activating Token Index: 789

Text #18

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.5028. Min Act: -0.0000

Data Index: 1453831 (Python Code)

Max Activating Token Index: 229

Text #19

Max Range: 2.1696. Min Range: -2.1696

Max Act: 1.5410. Min Act: -0.0000

Data Index: 1534721 (Python Code)

Max Activating Token Index: 884