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

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

Neuron 1636 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.4916. Min Act: -0.0000

Data Index: 1227798 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.4056. Min Act: -0.0000

Data Index: 642262 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.3226. Min Act: -0.0000

Data Index: 566268 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.0503. Min Act: -0.0000

Data Index: 202135 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.7562. Min Act: -0.0000

Data Index: 683622 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 5.7562. Min Range: -5.7562

Max Act: 4.6961. Min Act: -0.0000

Data Index: 731454 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 5.7562. Min Range: -5.7562

Max Act: 4.8234. Min Act: -0.0000

Data Index: 631273 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 5.7562. Min Range: -5.7562

Max Act: 4.8822. Min Act: -0.0000

Data Index: 150939 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 5.7562. Min Range: -5.7562

Max Act: 4.3384. Min Act: -0.0000

Data Index: 270445 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 5.7562. Min Range: -5.7562

Max Act: 4.5510. Min Act: -0.0000

Data Index: 31000 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 5.7562. Min Range: -5.7562

Max Act: 4.3257. Min Act: -0.0000

Data Index: 1287182 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 5.7562. Min Range: -5.7562

Max Act: 4.1771. Min Act: -0.0000

Data Index: 1608334 (Python Code)

Max Activating Token Index: 573

Text #12

Max Range: 5.7562. Min Range: -5.7562

Max Act: 4.1630. Min Act: -0.0000

Data Index: 1544961 (Python Code)

Max Activating Token Index: 515

Text #13

Max Range: 5.7562. Min Range: -5.7562

Max Act: 4.2077. Min Act: -0.0000

Data Index: 1379550 (Python Code)

Max Activating Token Index: 292

Text #14

Max Range: 5.7562. Min Range: -5.7562

Max Act: 4.3972. Min Act: -0.0000

Data Index: 1105584 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 5.7562. Min Range: -5.7562

Max Act: 4.0680. Min Act: -0.0000

Data Index: 1467282 (Python Code)

Max Activating Token Index: 542

Text #16

Max Range: 5.7562. Min Range: -5.7562

Max Act: 4.4778. Min Act: -0.0000

Data Index: 164096 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 5.7562. Min Range: -5.7562

Max Act: 4.0795. Min Act: -0.0000

Data Index: 1602333 (Python Code)

Max Activating Token Index: 143

Text #18

Max Range: 5.7562. Min Range: -5.7562

Max Act: 4.0423. Min Act: -0.0000

Data Index: 1519944 (Python Code)

Max Activating Token Index: 498

Text #19

Max Range: 5.7562. Min Range: -5.7562

Max Act: 4.0819. Min Act: -0.0000

Data Index: 864501 (C4 (Web Text))

Max Activating Token Index: 752