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

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

Neuron 1540 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: 0.5532. Min Range: -0.5532

Max Act: 0.5532. Min Act: -0.0000

Data Index: 888177 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.5469. Min Act: -0.0000

Data Index: 580835 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4868. Min Act: -0.0000

Data Index: 37505 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4690. Min Act: -0.0000

Data Index: 1462404 (Python Code)

Max Activating Token Index: 19

Text #4

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4750. Min Act: -0.0000

Data Index: 858064 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4369. Min Act: -0.0000

Data Index: 257886 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4024. Min Act: -0.0000

Data Index: 600449 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4322. Min Act: -0.0000

Data Index: 1152209 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4823. Min Act: -0.0000

Data Index: 251085 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4050. Min Act: -0.0000

Data Index: 1138935 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.3946. Min Act: -0.0000

Data Index: 545657 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4199. Min Act: -0.0000

Data Index: 114138 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4217. Min Act: -0.0000

Data Index: 160106 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.3678. Min Act: -0.0000

Data Index: 993127 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4128. Min Act: -0.0000

Data Index: 317639 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.3987. Min Act: -0.0000

Data Index: 1288812 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.3831. Min Act: -0.0000

Data Index: 193512 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.3761. Min Act: -0.0000

Data Index: 1265727 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.3804. Min Act: -0.0000

Data Index: 1116652 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4100. Min Act: -0.0000

Data Index: 510976 (C4 (Web Text))

Max Activating Token Index: 931