Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5636 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5209. Min Range: -1.5209

Max Act: 1.5209. Min Act: -0.0000

Data Index: 123026 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 1.5209. Min Range: -1.5209

Max Act: 1.3524. Min Act: -0.0001

Data Index: 1134098 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 1.5209. Min Range: -1.5209

Max Act: 1.2973. Min Act: -0.0000

Data Index: 703513 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 1.5209. Min Range: -1.5209

Max Act: 1.3049. Min Act: -0.0000

Data Index: 736320 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 1.5209. Min Range: -1.5209

Max Act: 1.3156. Min Act: -0.0001

Data Index: 7788 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 1.5209. Min Range: -1.5209

Max Act: 1.2632. Min Act: -0.0000

Data Index: 7424 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 1.5209. Min Range: -1.5209

Max Act: 1.2860. Min Act: -0.0000

Data Index: 909805 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 1.5209. Min Range: -1.5209

Max Act: 1.1796. Min Act: -0.0001

Data Index: 286705 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 1.5209. Min Range: -1.5209

Max Act: 1.3569. Min Act: -0.0001

Data Index: 485573 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 1.5209. Min Range: -1.5209

Max Act: 1.3071. Min Act: -0.0000

Data Index: 874038 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 1.5209. Min Range: -1.5209

Max Act: 1.2421. Min Act: -0.0000

Data Index: 348880 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 1.5209. Min Range: -1.5209

Max Act: 1.1829. Min Act: -0.0000

Data Index: 669995 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 1.5209. Min Range: -1.5209

Max Act: 1.2563. Min Act: -0.0000

Data Index: 568687 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 1.5209. Min Range: -1.5209

Max Act: 1.1017. Min Act: -0.0001

Data Index: 1340314 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 1.5209. Min Range: -1.5209

Max Act: 1.1693. Min Act: -0.0000

Data Index: 639939 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 1.5209. Min Range: -1.5209

Max Act: 1.1263. Min Act: -0.0000

Data Index: 830575 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 1.5209. Min Range: -1.5209

Max Act: 1.2435. Min Act: -0.0000

Data Index: 918673 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 1.5209. Min Range: -1.5209

Max Act: 1.1783. Min Act: -0.0000

Data Index: 722642 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 1.5209. Min Range: -1.5209

Max Act: 1.1344. Min Act: -0.0000

Data Index: 1221636 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 1.5209. Min Range: -1.5209

Max Act: 1.1400. Min Act: -0.0000

Data Index: 948278 (C4 (Web Text))

Max Activating Token Index: 111