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

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

Neuron 4652 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1764. Min Range: -3.1764

Max Act: 3.1764. Min Act: -0.0001

Data Index: 20830 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 3.1764. Min Range: -3.1764

Max Act: 2.7060. Min Act: -0.0001

Data Index: 552670 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 3.1764. Min Range: -3.1764

Max Act: 2.8473. Min Act: -0.0001

Data Index: 967287 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 3.1764. Min Range: -3.1764

Max Act: 2.6859. Min Act: -0.0001

Data Index: 917030 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 3.1764. Min Range: -3.1764

Max Act: 2.7351. Min Act: -0.0001

Data Index: 376619 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 3.1764. Min Range: -3.1764

Max Act: 2.5404. Min Act: -0.0001

Data Index: 1080823 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 3.1764. Min Range: -3.1764

Max Act: 2.5451. Min Act: -0.0001

Data Index: 751751 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 3.1764. Min Range: -3.1764

Max Act: 2.3712. Min Act: -0.0001

Data Index: 1130156 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 3.1764. Min Range: -3.1764

Max Act: 2.4825. Min Act: -0.0001

Data Index: 58840 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 3.1764. Min Range: -3.1764

Max Act: 2.4614. Min Act: -0.0001

Data Index: 676084 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 3.1764. Min Range: -3.1764

Max Act: 2.5768. Min Act: -0.0001

Data Index: 296010 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 3.1764. Min Range: -3.1764

Max Act: 2.5623. Min Act: -0.0001

Data Index: 827130 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 3.1764. Min Range: -3.1764

Max Act: 2.6963. Min Act: -0.0001

Data Index: 704045 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 3.1764. Min Range: -3.1764

Max Act: 2.5137. Min Act: -0.0001

Data Index: 677676 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 3.1764. Min Range: -3.1764

Max Act: 2.6361. Min Act: -0.0001

Data Index: 475482 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 3.1764. Min Range: -3.1764

Max Act: 2.3598. Min Act: -0.0001

Data Index: 502132 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 3.1764. Min Range: -3.1764

Max Act: 2.4620. Min Act: -0.0001

Data Index: 706479 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 3.1764. Min Range: -3.1764

Max Act: 2.4465. Min Act: -0.0001

Data Index: 267119 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 3.1764. Min Range: -3.1764

Max Act: 2.3971. Min Act: -0.0001

Data Index: 1141184 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 3.1764. Min Range: -3.1764

Max Act: 2.1571. Min Act: -0.0001

Data Index: 514179 (C4 (Web Text))

Max Activating Token Index: 210