Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5077 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.4429. Min Range: -4.4429

Max Act: 4.4429. Min Act: -0.0000

Data Index: 159205 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 4.4429. Min Range: -4.4429

Max Act: 4.0063. Min Act: -0.0001

Data Index: 583462 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 4.4429. Min Range: -4.4429

Max Act: 3.9255. Min Act: -0.0000

Data Index: 614031 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 4.4429. Min Range: -4.4429

Max Act: 3.2354. Min Act: -0.0001

Data Index: 757112 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 4.4429. Min Range: -4.4429

Max Act: 3.4909. Min Act: -0.0000

Data Index: 740867 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 4.4429. Min Range: -4.4429

Max Act: 3.7306. Min Act: -0.0001

Data Index: 907678 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 4.4429. Min Range: -4.4429

Max Act: 3.3725. Min Act: -0.0000

Data Index: 612452 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 4.4429. Min Range: -4.4429

Max Act: 3.2504. Min Act: -0.0001

Data Index: 1102 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 4.4429. Min Range: -4.4429

Max Act: 3.2674. Min Act: -0.0000

Data Index: 522912 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 4.4429. Min Range: -4.4429

Max Act: 3.1147. Min Act: -0.0001

Data Index: 78763 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 4.4429. Min Range: -4.4429

Max Act: 3.2341. Min Act: -0.0000

Data Index: 41664 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 4.4429. Min Range: -4.4429

Max Act: 3.2071. Min Act: -0.0001

Data Index: 16253 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 4.4429. Min Range: -4.4429

Max Act: 3.4412. Min Act: -0.0001

Data Index: 1220540 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 4.4429. Min Range: -4.4429

Max Act: 3.2064. Min Act: -0.0000

Data Index: 831456 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 4.4429. Min Range: -4.4429

Max Act: 3.1723. Min Act: -0.0000

Data Index: 1226577 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 4.4429. Min Range: -4.4429

Max Act: 3.1883. Min Act: -0.0001

Data Index: 776848 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 4.4429. Min Range: -4.4429

Max Act: 3.2607. Min Act: -0.0000

Data Index: 789217 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 4.4429. Min Range: -4.4429

Max Act: 3.1589. Min Act: -0.0001

Data Index: 769155 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 4.4429. Min Range: -4.4429

Max Act: 2.9261. Min Act: -0.0000

Data Index: 1108653 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 4.4429. Min Range: -4.4429

Max Act: 3.0043. Min Act: -0.0000

Data Index: 807551 (C4 (Web Text))

Max Activating Token Index: 672