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

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

Neuron 659 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.2909. Min Act: -0.0001

Data Index: 1338217 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.2273. Min Act: -0.0001

Data Index: 620109 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.2454. Min Act: -0.0001

Data Index: 771333 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.0942. Min Act: -0.0001

Data Index: 1143389 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.0715. Min Act: -0.0001

Data Index: 775235 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.0028. Min Act: -0.0001

Data Index: 920202 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.0861. Min Act: -0.0001

Data Index: 127743 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.0511. Min Act: -0.0001

Data Index: 150503 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.0093. Min Act: -0.0001

Data Index: 1243298 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.0560. Min Act: -0.0001

Data Index: 1179060 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 1.2909. Min Range: -1.2909

Max Act: 0.9718. Min Act: -0.0001

Data Index: 603482 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.0503. Min Act: -0.0001

Data Index: 858184 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.1006. Min Act: -0.0001

Data Index: 283460 (C4 (Web Text))

Max Activating Token Index: 264

Text #13

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.0545. Min Act: -0.0001

Data Index: 614534 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.0254. Min Act: -0.0001

Data Index: 346217 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.0541. Min Act: -0.0001

Data Index: 762824 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.0579. Min Act: -0.0001

Data Index: 1273463 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 1.2909. Min Range: -1.2909

Max Act: 0.9607. Min Act: -0.0001

Data Index: 439423 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 1.2909. Min Range: -1.2909

Max Act: 0.9960. Min Act: -0.0001

Data Index: 559255 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 1.2909. Min Range: -1.2909

Max Act: 0.9685. Min Act: -0.0001

Data Index: 175422 (C4 (Web Text))

Max Activating Token Index: 17