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

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

Neuron 4554 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3802. Min Range: -2.3802

Max Act: 2.3802. Min Act: -0.0000

Data Index: 192401 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.7769. Min Act: -0.0000

Data Index: 1141761 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.9198. Min Act: -0.0000

Data Index: 416753 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 2.3802. Min Range: -2.3802

Max Act: 2.0053. Min Act: -0.0000

Data Index: 971979 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 2.3802. Min Range: -2.3802

Max Act: 2.0656. Min Act: -0.0000

Data Index: 306551 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.9080. Min Act: -0.0000

Data Index: 531410 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.6248. Min Act: -0.0000

Data Index: 984870 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.6509. Min Act: -0.0000

Data Index: 642910 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.6042. Min Act: -0.0000

Data Index: 535067 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.5302. Min Act: -0.0000

Data Index: 556145 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.4219. Min Act: -0.0000

Data Index: 765099 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.4976. Min Act: -0.0001

Data Index: 693090 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.4129. Min Act: -0.0000

Data Index: 137564 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.6584. Min Act: -0.0000

Data Index: 1151081 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.4806. Min Act: -0.0000

Data Index: 87449 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.4264. Min Act: -0.0000

Data Index: 1209726 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.4621. Min Act: -0.0000

Data Index: 1318539 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.3685. Min Act: -0.0000

Data Index: 876744 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.5314. Min Act: -0.0000

Data Index: 1099653 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.5239. Min Act: -0.0000

Data Index: 656111 (C4 (Web Text))

Max Activating Token Index: 966