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

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

Neuron 1922 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.6780. Min Act: -0.0000

Data Index: 1163832 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.3878. Min Act: -0.0000

Data Index: 1378747 (Python Code)

Max Activating Token Index: 288

Text #2

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.4901. Min Act: -0.0000

Data Index: 1506430 (Python Code)

Max Activating Token Index: 71

Text #3

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.6477. Min Act: -0.0000

Data Index: 757450 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.3643. Min Act: -0.0000

Data Index: 1634658 (Python Code)

Max Activating Token Index: 318

Text #5

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.3251. Min Act: -0.0000

Data Index: 377872 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.1941. Min Act: -0.0000

Data Index: 1383739 (Python Code)

Max Activating Token Index: 180

Text #7

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.3046. Min Act: -0.0000

Data Index: 963477 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.2264. Min Act: -0.0000

Data Index: 1508536 (Python Code)

Max Activating Token Index: 185

Text #9

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.2236. Min Act: -0.0000

Data Index: 120810 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.3302. Min Act: -0.0000

Data Index: 568035 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.1522. Min Act: -0.0000

Data Index: 1547622 (Python Code)

Max Activating Token Index: 222

Text #12

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.1116. Min Act: -0.0000

Data Index: 1412472 (Python Code)

Max Activating Token Index: 659

Text #13

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.0958. Min Act: -0.0000

Data Index: 1621287 (Python Code)

Max Activating Token Index: 202

Text #14

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.0788. Min Act: -0.0000

Data Index: 873683 (C4 (Web Text))

Max Activating Token Index: 751

Text #15

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.0727. Min Act: -0.0000

Data Index: 980611 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.9669. Min Act: -0.0000

Data Index: 1434415 (Python Code)

Max Activating Token Index: 157

Text #17

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.7836. Min Act: -0.0000

Data Index: 1468597 (Python Code)

Max Activating Token Index: 67

Text #18

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.9806. Min Act: -0.0000

Data Index: 1599715 (Python Code)

Max Activating Token Index: 151

Text #19

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.1001. Min Act: -0.0000

Data Index: 1610198 (Python Code)

Max Activating Token Index: 557