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

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

Neuron 951 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5324. Min Range: -1.5324

Max Act: 1.5324. Min Act: -0.0000

Data Index: 492385 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 1.5324. Min Range: -1.5324

Max Act: 0.9828. Min Act: 0.0000

Data Index: 214261 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 1.5324. Min Range: -1.5324

Max Act: 0.9642. Min Act: -0.0000

Data Index: 521267 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 1.5324. Min Range: -1.5324

Max Act: 1.0054. Min Act: -0.0000

Data Index: 144285 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 1.5324. Min Range: -1.5324

Max Act: 0.9487. Min Act: -0.0000

Data Index: 1160227 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 1.5324. Min Range: -1.5324

Max Act: 0.9238. Min Act: -0.0000

Data Index: 1348022 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 1.5324. Min Range: -1.5324

Max Act: 1.0262. Min Act: -0.0000

Data Index: 595795 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 1.5324. Min Range: -1.5324

Max Act: 0.9708. Min Act: -0.0000

Data Index: 665168 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 1.5324. Min Range: -1.5324

Max Act: 0.9523. Min Act: -0.0000

Data Index: 1279458 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 1.5324. Min Range: -1.5324

Max Act: 0.8688. Min Act: -0.0000

Data Index: 1285062 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 1.5324. Min Range: -1.5324

Max Act: 0.9225. Min Act: -0.0000

Data Index: 598794 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 1.5324. Min Range: -1.5324

Max Act: 0.9444. Min Act: -0.0000

Data Index: 523923 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 1.5324. Min Range: -1.5324

Max Act: 0.9497. Min Act: -0.0000

Data Index: 203845 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 1.5324. Min Range: -1.5324

Max Act: 0.9866. Min Act: -0.0000

Data Index: 1228584 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 1.5324. Min Range: -1.5324

Max Act: 0.9581. Min Act: -0.0000

Data Index: 1306159 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 1.5324. Min Range: -1.5324

Max Act: 0.9737. Min Act: -0.0000

Data Index: 436504 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 1.5324. Min Range: -1.5324

Max Act: 0.8504. Min Act: -0.0000

Data Index: 484896 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 1.5324. Min Range: -1.5324

Max Act: 0.9168. Min Act: -0.0000

Data Index: 1229672 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 1.5324. Min Range: -1.5324

Max Act: 0.8904. Min Act: -0.0000

Data Index: 218683 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 1.5324. Min Range: -1.5324

Max Act: 0.9140. Min Act: -0.0000

Data Index: 1338793 (C4 (Web Text))

Max Activating Token Index: 419