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

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

Neuron 511 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7830. Min Range: -2.7830

Max Act: 2.7830. Min Act: -0.0000

Data Index: 1271071 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 2.7830. Min Range: -2.7830

Max Act: 2.1536. Min Act: -0.0000

Data Index: 439793 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 2.7830. Min Range: -2.7830

Max Act: 1.8124. Min Act: -0.0000

Data Index: 583529 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 2.7830. Min Range: -2.7830

Max Act: 1.6692. Min Act: -0.0000

Data Index: 842773 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 2.7830. Min Range: -2.7830

Max Act: 1.7505. Min Act: -0.0000

Data Index: 1329562 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 2.7830. Min Range: -2.7830

Max Act: 1.6349. Min Act: -0.0000

Data Index: 878769 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 2.7830. Min Range: -2.7830

Max Act: 1.6215. Min Act: -0.0000

Data Index: 345193 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 2.7830. Min Range: -2.7830

Max Act: 1.6139. Min Act: -0.0000

Data Index: 1158433 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 2.7830. Min Range: -2.7830

Max Act: 1.6155. Min Act: -0.0000

Data Index: 744698 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 2.7830. Min Range: -2.7830

Max Act: 1.5862. Min Act: -0.0000

Data Index: 95147 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 2.7830. Min Range: -2.7830

Max Act: 1.5790. Min Act: -0.0000

Data Index: 1355724 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 2.7830. Min Range: -2.7830

Max Act: 1.6607. Min Act: -0.0000

Data Index: 805088 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 2.7830. Min Range: -2.7830

Max Act: 1.6336. Min Act: -0.0000

Data Index: 272625 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 2.7830. Min Range: -2.7830

Max Act: 1.5456. Min Act: -0.0000

Data Index: 531246 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 2.7830. Min Range: -2.7830

Max Act: 1.4983. Min Act: -0.0000

Data Index: 340603 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 2.7830. Min Range: -2.7830

Max Act: 1.4804. Min Act: -0.0000

Data Index: 320983 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 2.7830. Min Range: -2.7830

Max Act: 1.4768. Min Act: -0.0000

Data Index: 652600 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 2.7830. Min Range: -2.7830

Max Act: 1.3830. Min Act: -0.0000

Data Index: 880603 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 2.7830. Min Range: -2.7830

Max Act: 1.4556. Min Act: -0.0000

Data Index: 183549 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 2.7830. Min Range: -2.7830

Max Act: 1.4626. Min Act: -0.0000

Data Index: 1092998 (C4 (Web Text))

Max Activating Token Index: 840