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

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

Neuron 123 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: 2.7799. Min Range: -2.7799

Max Act: 2.7799. Min Act: -0.0000

Data Index: 26374 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 2.7799. Min Range: -2.7799

Max Act: 2.6473. Min Act: -0.0000

Data Index: 241826 (C4 (Web Text))

Max Activating Token Index: 809

Text #2

Max Range: 2.7799. Min Range: -2.7799

Max Act: 2.5407. Min Act: -0.0001

Data Index: 1155427 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 2.7799. Min Range: -2.7799

Max Act: 2.5171. Min Act: -0.0000

Data Index: 569051 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 2.7799. Min Range: -2.7799

Max Act: 2.3923. Min Act: -0.0000

Data Index: 481114 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 2.7799. Min Range: -2.7799

Max Act: 2.3680. Min Act: -0.0000

Data Index: 9235 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 2.7799. Min Range: -2.7799

Max Act: 2.4218. Min Act: -0.0000

Data Index: 606200 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 2.7799. Min Range: -2.7799

Max Act: 2.3931. Min Act: -0.0000

Data Index: 12626 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 2.7799. Min Range: -2.7799

Max Act: 2.4010. Min Act: -0.0000

Data Index: 972255 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 2.7799. Min Range: -2.7799

Max Act: 2.1598. Min Act: -0.0000

Data Index: 329495 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 2.7799. Min Range: -2.7799

Max Act: 2.2796. Min Act: -0.0000

Data Index: 555363 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 2.7799. Min Range: -2.7799

Max Act: 2.3884. Min Act: -0.0000

Data Index: 465223 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 2.7799. Min Range: -2.7799

Max Act: 2.2396. Min Act: -0.0000

Data Index: 925677 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 2.7799. Min Range: -2.7799

Max Act: 2.1838. Min Act: -0.0000

Data Index: 584908 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 2.7799. Min Range: -2.7799

Max Act: 2.1677. Min Act: -0.0000

Data Index: 633379 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 2.7799. Min Range: -2.7799

Max Act: 2.1662. Min Act: -0.0000

Data Index: 1041273 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 2.7799. Min Range: -2.7799

Max Act: 2.2598. Min Act: -0.0000

Data Index: 1250182 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 2.7799. Min Range: -2.7799

Max Act: 2.0455. Min Act: -0.0000

Data Index: 951261 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 2.7799. Min Range: -2.7799

Max Act: 1.9264. Min Act: -0.0000

Data Index: 514611 (C4 (Web Text))

Max Activating Token Index: 513

Text #19

Max Range: 2.7799. Min Range: -2.7799

Max Act: 1.8163. Min Act: -0.0000

Data Index: 677294 (C4 (Web Text))

Max Activating Token Index: 836