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

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

Neuron 956 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.5487. Min Act: -0.0003

Data Index: 1195975 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.5243. Min Act: -0.0002

Data Index: 951495 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.5156. Min Act: -0.0002

Data Index: 1276225 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.5157. Min Act: -0.0003

Data Index: 993145 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.5071. Min Act: -0.0003

Data Index: 282980 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.4899. Min Act: -0.0003

Data Index: 680632 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.4634. Min Act: -0.0003

Data Index: 792294 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.4867. Min Act: -0.0003

Data Index: 596063 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.4697. Min Act: -0.0002

Data Index: 405769 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.4840. Min Act: -0.0002

Data Index: 1293001 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.4796. Min Act: -0.0002

Data Index: 692140 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.4760. Min Act: -0.0003

Data Index: 1195056 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.4606. Min Act: -0.0002

Data Index: 1289041 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.4734. Min Act: -0.0003

Data Index: 258757 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.4441. Min Act: -0.0003

Data Index: 1167938 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.4598. Min Act: -0.0003

Data Index: 574243 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.4743. Min Act: -0.0003

Data Index: 866640 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.4562. Min Act: -0.0002

Data Index: 368456 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.4380. Min Act: -0.0003

Data Index: 866187 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.4526. Min Act: -0.0003

Data Index: 1315279 (C4 (Web Text))

Max Activating Token Index: 956