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

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

Neuron 36 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: 1.5142. Min Range: -1.5142

Max Act: 1.5142. Min Act: -0.0000

Data Index: 1272720 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 1.5142. Min Range: -1.5142

Max Act: 1.2120. Min Act: -0.0000

Data Index: 41602 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 1.5142. Min Range: -1.5142

Max Act: 1.2571. Min Act: -0.0001

Data Index: 66478 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 1.5142. Min Range: -1.5142

Max Act: 1.2403. Min Act: -0.0000

Data Index: 1220643 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 1.5142. Min Range: -1.5142

Max Act: 1.1790. Min Act: -0.0000

Data Index: 744551 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 1.5142. Min Range: -1.5142

Max Act: 1.2017. Min Act: -0.0000

Data Index: 1267962 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 1.5142. Min Range: -1.5142

Max Act: 1.1257. Min Act: -0.0000

Data Index: 605784 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 1.5142. Min Range: -1.5142

Max Act: 1.1802. Min Act: -0.0000

Data Index: 180574 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 1.5142. Min Range: -1.5142

Max Act: 1.1680. Min Act: -0.0000

Data Index: 1215380 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 1.5142. Min Range: -1.5142

Max Act: 1.1882. Min Act: -0.0000

Data Index: 524085 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 1.5142. Min Range: -1.5142

Max Act: 1.2090. Min Act: -0.0000

Data Index: 727879 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 1.5142. Min Range: -1.5142

Max Act: 1.1097. Min Act: -0.0000

Data Index: 1041884 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 1.5142. Min Range: -1.5142

Max Act: 1.0993. Min Act: -0.0000

Data Index: 313267 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 1.5142. Min Range: -1.5142

Max Act: 1.1096. Min Act: -0.0000

Data Index: 1164567 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 1.5142. Min Range: -1.5142

Max Act: 1.0834. Min Act: -0.0000

Data Index: 973084 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 1.5142. Min Range: -1.5142

Max Act: 1.0802. Min Act: -0.0000

Data Index: 750586 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 1.5142. Min Range: -1.5142

Max Act: 1.0772. Min Act: -0.0000

Data Index: 25936 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 1.5142. Min Range: -1.5142

Max Act: 1.0753. Min Act: -0.0000

Data Index: 250932 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 1.5142. Min Range: -1.5142

Max Act: 1.0279. Min Act: -0.0000

Data Index: 147585 (C4 (Web Text))

Max Activating Token Index: 387

Text #19

Max Range: 1.5142. Min Range: -1.5142

Max Act: 1.0465. Min Act: -0.0000

Data Index: 1132953 (C4 (Web Text))

Max Activating Token Index: 261