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

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

Neuron 1769 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: 0.5803. Min Range: -0.5803

Max Act: 0.5803. Min Act: -0.0001

Data Index: 1249856 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.5371. Min Act: -0.0001

Data Index: 483754 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.5272. Min Act: -0.0001

Data Index: 376619 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.5066. Min Act: -0.0001

Data Index: 754051 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.4988. Min Act: -0.0001

Data Index: 4997 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.4756. Min Act: -0.0001

Data Index: 608929 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.5441. Min Act: -0.0001

Data Index: 1345412 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.4537. Min Act: -0.0001

Data Index: 375869 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.5284. Min Act: -0.0001

Data Index: 152394 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.5023. Min Act: -0.0001

Data Index: 554008 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.4711. Min Act: -0.0001

Data Index: 470833 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.4809. Min Act: -0.0001

Data Index: 852240 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.4767. Min Act: -0.0001

Data Index: 259061 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.4786. Min Act: -0.0001

Data Index: 855798 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.4600. Min Act: -0.0001

Data Index: 922660 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.4542. Min Act: -0.0001

Data Index: 1294947 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.3875. Min Act: -0.0001

Data Index: 1020108 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.4643. Min Act: -0.0001

Data Index: 972175 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.4467. Min Act: -0.0001

Data Index: 1163943 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.4429. Min Act: -0.0001

Data Index: 1339453 (C4 (Web Text))

Max Activating Token Index: 21