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

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

Neuron 1618 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3651. Min Range: -2.3651

Max Act: 2.3651. Min Act: -0.0000

Data Index: 240834 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 2.3651. Min Range: -2.3651

Max Act: 2.0709. Min Act: -0.0000

Data Index: 286276 (C4 (Web Text))

Max Activating Token Index: 758

Text #2

Max Range: 2.3651. Min Range: -2.3651

Max Act: 1.9275. Min Act: -0.0000

Data Index: 993796 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 2.3651. Min Range: -2.3651

Max Act: 1.6540. Min Act: -0.0000

Data Index: 12982 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 2.3651. Min Range: -2.3651

Max Act: 1.7584. Min Act: -0.0000

Data Index: 547182 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 2.3651. Min Range: -2.3651

Max Act: 1.8221. Min Act: -0.0000

Data Index: 250781 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 2.3651. Min Range: -2.3651

Max Act: 1.6701. Min Act: -0.0000

Data Index: 1027793 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 2.3651. Min Range: -2.3651

Max Act: 1.5601. Min Act: -0.0000

Data Index: 295658 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 2.3651. Min Range: -2.3651

Max Act: 1.5372. Min Act: -0.0000

Data Index: 507720 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 2.3651. Min Range: -2.3651

Max Act: 1.4423. Min Act: -0.0000

Data Index: 613936 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 2.3651. Min Range: -2.3651

Max Act: 1.4258. Min Act: -0.0000

Data Index: 1204983 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 2.3651. Min Range: -2.3651

Max Act: 1.4883. Min Act: -0.0000

Data Index: 52064 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 2.3651. Min Range: -2.3651

Max Act: 1.5160. Min Act: -0.0000

Data Index: 399588 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 2.3651. Min Range: -2.3651

Max Act: 1.3124. Min Act: -0.0000

Data Index: 1403580 (Python Code)

Max Activating Token Index: 1003

Text #14

Max Range: 2.3651. Min Range: -2.3651

Max Act: 1.3445. Min Act: -0.0000

Data Index: 938953 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 2.3651. Min Range: -2.3651

Max Act: 1.3301. Min Act: -0.0000

Data Index: 624949 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 2.3651. Min Range: -2.3651

Max Act: 1.4370. Min Act: -0.0000

Data Index: 1272645 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 2.3651. Min Range: -2.3651

Max Act: 1.4055. Min Act: -0.0000

Data Index: 1325391 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 2.3651. Min Range: -2.3651

Max Act: 1.3451. Min Act: -0.0000

Data Index: 1568621 (Python Code)

Max Activating Token Index: 239

Text #19

Max Range: 2.3651. Min Range: -2.3651

Max Act: 1.2694. Min Act: -0.0000

Data Index: 1157412 (C4 (Web Text))

Max Activating Token Index: 118