Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 445 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.5524. Min Act: -0.0001

Data Index: 723145 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4970. Min Act: -0.0002

Data Index: 1194606 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.5162. Min Act: -0.0002

Data Index: 1117044 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4792. Min Act: -0.0001

Data Index: 825595 (C4 (Web Text))

Max Activating Token Index: 486

Text #4

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.5010. Min Act: -0.0001

Data Index: 1044151 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4307. Min Act: -0.0002

Data Index: 1072496 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4905. Min Act: -0.0002

Data Index: 119734 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4699. Min Act: -0.0002

Data Index: 216803 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3978. Min Act: -0.0001

Data Index: 832702 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4812. Min Act: -0.0002

Data Index: 59934 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4919. Min Act: -0.0002

Data Index: 263132 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4745. Min Act: -0.0002

Data Index: 911087 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4443. Min Act: -0.0002

Data Index: 1241157 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4995. Min Act: -0.0001

Data Index: 938112 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4132. Min Act: -0.0002

Data Index: 410296 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.5321. Min Act: -0.0002

Data Index: 150436 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4351. Min Act: -0.0002

Data Index: 657292 (C4 (Web Text))

Max Activating Token Index: 656

Text #17

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4491. Min Act: -0.0001

Data Index: 1243608 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.5110. Min Act: -0.0002

Data Index: 662876 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3909. Min Act: -0.0001

Data Index: 317712 (C4 (Web Text))

Max Activating Token Index: 638