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

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

Neuron 2722 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8654. Min Range: -1.8654

Max Act: 1.8654. Min Act: -0.0001

Data Index: 595166 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 1.8654. Min Range: -1.8654

Max Act: 1.5970. Min Act: -0.0001

Data Index: 415357 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 1.8654. Min Range: -1.8654

Max Act: 1.5876. Min Act: -0.0001

Data Index: 787278 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 1.8654. Min Range: -1.8654

Max Act: 1.5582. Min Act: -0.0001

Data Index: 229918 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 1.8654. Min Range: -1.8654

Max Act: 1.4938. Min Act: -0.0001

Data Index: 1159788 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 1.8654. Min Range: -1.8654

Max Act: 1.3801. Min Act: -0.0001

Data Index: 175084 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 1.8654. Min Range: -1.8654

Max Act: 1.4428. Min Act: -0.0001

Data Index: 963214 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 1.8654. Min Range: -1.8654

Max Act: 1.3043. Min Act: -0.0001

Data Index: 739061 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 1.8654. Min Range: -1.8654

Max Act: 1.3721. Min Act: -0.0001

Data Index: 255480 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 1.8654. Min Range: -1.8654

Max Act: 1.3464. Min Act: -0.0001

Data Index: 145072 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 1.8654. Min Range: -1.8654

Max Act: 1.2949. Min Act: -0.0001

Data Index: 388785 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 1.8654. Min Range: -1.8654

Max Act: 1.1771. Min Act: -0.0001

Data Index: 601650 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 1.8654. Min Range: -1.8654

Max Act: 1.2970. Min Act: -0.0001

Data Index: 1034943 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 1.8654. Min Range: -1.8654

Max Act: 1.3452. Min Act: -0.0001

Data Index: 1319076 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 1.8654. Min Range: -1.8654

Max Act: 1.2421. Min Act: -0.0000

Data Index: 918795 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 1.8654. Min Range: -1.8654

Max Act: 1.2314. Min Act: -0.0001

Data Index: 989627 (C4 (Web Text))

Max Activating Token Index: 363

Text #16

Max Range: 1.8654. Min Range: -1.8654

Max Act: 1.2232. Min Act: -0.0001

Data Index: 1087227 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 1.8654. Min Range: -1.8654

Max Act: 1.2295. Min Act: -0.0001

Data Index: 632340 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 1.8654. Min Range: -1.8654

Max Act: 1.2170. Min Act: -0.0001

Data Index: 1144941 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 1.8654. Min Range: -1.8654

Max Act: 1.2160. Min Act: -0.0001

Data Index: 579024 (C4 (Web Text))

Max Activating Token Index: 614