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

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

Neuron 241 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.9063. Min Range: -6.9063

Max Act: 6.9063. Min Act: -0.0000

Data Index: 336096 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 6.9063. Min Range: -6.9063

Max Act: 6.6300. Min Act: -0.0000

Data Index: 666858 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 6.9063. Min Range: -6.9063

Max Act: 6.7254. Min Act: -0.0000

Data Index: 156446 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 6.9063. Min Range: -6.9063

Max Act: 6.3899. Min Act: -0.0000

Data Index: 698962 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 6.9063. Min Range: -6.9063

Max Act: 6.3491. Min Act: -0.0000

Data Index: 899214 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 6.9063. Min Range: -6.9063

Max Act: 6.5026. Min Act: -0.0000

Data Index: 851376 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 6.9063. Min Range: -6.9063

Max Act: 6.2677. Min Act: -0.0000

Data Index: 1103623 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 6.9063. Min Range: -6.9063

Max Act: 6.1269. Min Act: -0.0000

Data Index: 475405 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 6.9063. Min Range: -6.9063

Max Act: 5.9625. Min Act: -0.0000

Data Index: 716753 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 6.9063. Min Range: -6.9063

Max Act: 5.6677. Min Act: -0.0000

Data Index: 912995 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 6.9063. Min Range: -6.9063

Max Act: 6.1088. Min Act: -0.0000

Data Index: 350457 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 6.9063. Min Range: -6.9063

Max Act: 5.2979. Min Act: -0.0000

Data Index: 578109 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 6.9063. Min Range: -6.9063

Max Act: 5.1435. Min Act: -0.0000

Data Index: 568958 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 6.9063. Min Range: -6.9063

Max Act: 5.2948. Min Act: -0.0000

Data Index: 939852 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 6.9063. Min Range: -6.9063

Max Act: 5.4954. Min Act: -0.0000

Data Index: 162113 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 6.9063. Min Range: -6.9063

Max Act: 5.5231. Min Act: -0.0000

Data Index: 334328 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 6.9063. Min Range: -6.9063

Max Act: 5.3938. Min Act: -0.0000

Data Index: 1194459 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 6.9063. Min Range: -6.9063

Max Act: 4.8991. Min Act: -0.0000

Data Index: 1010970 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 6.9063. Min Range: -6.9063

Max Act: 4.9690. Min Act: -0.0000

Data Index: 803675 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 6.9063. Min Range: -6.9063

Max Act: 4.8444. Min Act: -0.0000

Data Index: 1173810 (C4 (Web Text))

Max Activating Token Index: 100