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

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

Neuron 3310 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3539. Min Range: -1.3539

Max Act: 1.3453. Min Act: -0.0001

Data Index: 1281579 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 1.3539. Min Range: -1.3539

Max Act: 1.3539. Min Act: -0.0001

Data Index: 871716 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 1.3539. Min Range: -1.3539

Max Act: 1.2638. Min Act: -0.0001

Data Index: 1153012 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 1.3539. Min Range: -1.3539

Max Act: 1.1189. Min Act: -0.0001

Data Index: 1069119 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 1.3539. Min Range: -1.3539

Max Act: 1.1252. Min Act: -0.0001

Data Index: 1224015 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 1.3539. Min Range: -1.3539

Max Act: 1.1386. Min Act: -0.0001

Data Index: 491580 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 1.3539. Min Range: -1.3539

Max Act: 1.1362. Min Act: -0.0001

Data Index: 735269 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 1.3539. Min Range: -1.3539

Max Act: 1.1049. Min Act: -0.0001

Data Index: 807073 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 1.3539. Min Range: -1.3539

Max Act: 1.1382. Min Act: -0.0001

Data Index: 411580 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 1.3539. Min Range: -1.3539

Max Act: 1.1372. Min Act: -0.0001

Data Index: 237748 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 1.3539. Min Range: -1.3539

Max Act: 1.0764. Min Act: -0.0001

Data Index: 1244804 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 1.3539. Min Range: -1.3539

Max Act: 1.1035. Min Act: -0.0001

Data Index: 26007 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 1.3539. Min Range: -1.3539

Max Act: 1.1124. Min Act: -0.0001

Data Index: 548085 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 1.3539. Min Range: -1.3539

Max Act: 1.1978. Min Act: -0.0001

Data Index: 890412 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 1.3539. Min Range: -1.3539

Max Act: 1.0775. Min Act: -0.0001

Data Index: 886726 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 1.3539. Min Range: -1.3539

Max Act: 1.0653. Min Act: -0.0001

Data Index: 1340002 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 1.3539. Min Range: -1.3539

Max Act: 1.0716. Min Act: -0.0001

Data Index: 749413 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 1.3539. Min Range: -1.3539

Max Act: 1.1002. Min Act: -0.0001

Data Index: 1012048 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 1.3539. Min Range: -1.3539

Max Act: 1.0095. Min Act: -0.0001

Data Index: 1189811 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 1.3539. Min Range: -1.3539

Max Act: 1.1179. Min Act: -0.0001

Data Index: 1085276 (C4 (Web Text))

Max Activating Token Index: 8