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

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

Neuron 1593 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1351. Min Range: -2.1351

Max Act: 2.1351. Min Act: -0.0000

Data Index: 1606597 (Python Code)

Max Activating Token Index: 91

Text #1

Max Range: 2.1351. Min Range: -2.1351

Max Act: 2.0129. Min Act: -0.0000

Data Index: 1478734 (Python Code)

Max Activating Token Index: 317

Text #2

Max Range: 2.1351. Min Range: -2.1351

Max Act: 1.8155. Min Act: -0.0000

Data Index: 1441416 (Python Code)

Max Activating Token Index: 883

Text #3

Max Range: 2.1351. Min Range: -2.1351

Max Act: 1.8929. Min Act: -0.0000

Data Index: 1388774 (Python Code)

Max Activating Token Index: 591

Text #4

Max Range: 2.1351. Min Range: -2.1351

Max Act: 1.6218. Min Act: -0.0000

Data Index: 1485085 (Python Code)

Max Activating Token Index: 192

Text #5

Max Range: 2.1351. Min Range: -2.1351

Max Act: 1.6785. Min Act: -0.0000

Data Index: 1540598 (Python Code)

Max Activating Token Index: 889

Text #6

Max Range: 2.1351. Min Range: -2.1351

Max Act: 1.6730. Min Act: -0.0000

Data Index: 1495417 (Python Code)

Max Activating Token Index: 747

Text #7

Max Range: 2.1351. Min Range: -2.1351

Max Act: 1.5462. Min Act: -0.0000

Data Index: 1503660 (Python Code)

Max Activating Token Index: 248

Text #8

Max Range: 2.1351. Min Range: -2.1351

Max Act: 1.5838. Min Act: -0.0000

Data Index: 1639139 (Python Code)

Max Activating Token Index: 662

Text #9

Max Range: 2.1351. Min Range: -2.1351

Max Act: 1.5694. Min Act: -0.0000

Data Index: 1518926 (Python Code)

Max Activating Token Index: 782

Text #10

Max Range: 2.1351. Min Range: -2.1351

Max Act: 1.5382. Min Act: -0.0000

Data Index: 1458665 (Python Code)

Max Activating Token Index: 803

Text #11

Max Range: 2.1351. Min Range: -2.1351

Max Act: 1.4801. Min Act: -0.0000

Data Index: 666594 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 2.1351. Min Range: -2.1351

Max Act: 1.4509. Min Act: -0.0000

Data Index: 1488007 (Python Code)

Max Activating Token Index: 46

Text #13

Max Range: 2.1351. Min Range: -2.1351

Max Act: 1.4543. Min Act: -0.0000

Data Index: 1614096 (Python Code)

Max Activating Token Index: 700

Text #14

Max Range: 2.1351. Min Range: -2.1351

Max Act: 1.5213. Min Act: -0.0000

Data Index: 1430842 (Python Code)

Max Activating Token Index: 29

Text #15

Max Range: 2.1351. Min Range: -2.1351

Max Act: 1.5249. Min Act: -0.0000

Data Index: 1445080 (Python Code)

Max Activating Token Index: 137

Text #16

Max Range: 2.1351. Min Range: -2.1351

Max Act: 1.4373. Min Act: -0.0000

Data Index: 106767 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 2.1351. Min Range: -2.1351

Max Act: 1.4615. Min Act: -0.0000

Data Index: 1240981 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 2.1351. Min Range: -2.1351

Max Act: 1.4163. Min Act: -0.0000

Data Index: 1475189 (Python Code)

Max Activating Token Index: 249

Text #19

Max Range: 2.1351. Min Range: -2.1351

Max Act: 1.4316. Min Act: -0.0000

Data Index: 1501035 (Python Code)

Max Activating Token Index: 815