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

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

Neuron 1328 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.6694. Min Act: -0.0000

Data Index: 899568 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5738. Min Act: -0.0000

Data Index: 1089876 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5686. Min Act: -0.0000

Data Index: 1031361 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5379. Min Act: -0.0000

Data Index: 38300 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.4565. Min Act: -0.0000

Data Index: 77570 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.4822. Min Act: -0.0000

Data Index: 1267876 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.4714. Min Act: -0.0000

Data Index: 1348064 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.4407. Min Act: -0.0000

Data Index: 321677 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.4601. Min Act: -0.0000

Data Index: 402485 (C4 (Web Text))

Max Activating Token Index: 512

Text #9

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.4565. Min Act: -0.0000

Data Index: 285270 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.4253. Min Act: -0.0000

Data Index: 44302 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.4702. Min Act: -0.0000

Data Index: 775954 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.4450. Min Act: -0.0000

Data Index: 655464 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.4148. Min Act: -0.0000

Data Index: 175406 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.4123. Min Act: -0.0000

Data Index: 156237 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.3746. Min Act: -0.0000

Data Index: 141857 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.4037. Min Act: -0.0000

Data Index: 96618 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.4018. Min Act: -0.0000

Data Index: 15615 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.3746. Min Act: -0.0000

Data Index: 901348 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.3874. Min Act: -0.0000

Data Index: 796252 (C4 (Web Text))

Max Activating Token Index: 594