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

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

Neuron 4380 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8356. Min Range: -1.8356

Max Act: 1.6991. Min Act: -0.0000

Data Index: 1016485 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 1.8356. Min Range: -1.8356

Max Act: 1.6408. Min Act: -0.0000

Data Index: 109707 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 1.8356. Min Range: -1.8356

Max Act: 1.8356. Min Act: -0.0000

Data Index: 910847 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 1.8356. Min Range: -1.8356

Max Act: 1.7097. Min Act: 0.0000

Data Index: 307934 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 1.8356. Min Range: -1.8356

Max Act: 1.3170. Min Act: -0.0000

Data Index: 960183 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 1.8356. Min Range: -1.8356

Max Act: 1.3849. Min Act: -0.0000

Data Index: 1379639 (Python Code)

Max Activating Token Index: 52

Text #6

Max Range: 1.8356. Min Range: -1.8356

Max Act: 1.3950. Min Act: -0.0000

Data Index: 472945 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 1.8356. Min Range: -1.8356

Max Act: 1.4006. Min Act: -0.0000

Data Index: 692365 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 1.8356. Min Range: -1.8356

Max Act: 1.4031. Min Act: -0.0000

Data Index: 1590892 (Python Code)

Max Activating Token Index: 450

Text #9

Max Range: 1.8356. Min Range: -1.8356

Max Act: 1.2172. Min Act: -0.0000

Data Index: 490287 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 1.8356. Min Range: -1.8356

Max Act: 1.1992. Min Act: -0.0000

Data Index: 1293742 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 1.8356. Min Range: -1.8356

Max Act: 1.2650. Min Act: -0.0000

Data Index: 1629024 (Python Code)

Max Activating Token Index: 511

Text #12

Max Range: 1.8356. Min Range: -1.8356

Max Act: 1.0993. Min Act: -0.0000

Data Index: 151087 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 1.8356. Min Range: -1.8356

Max Act: 1.1824. Min Act: -0.0000

Data Index: 1381119 (Python Code)

Max Activating Token Index: 332

Text #14

Max Range: 1.8356. Min Range: -1.8356

Max Act: 1.1374. Min Act: -0.0000

Data Index: 1372912 (Python Code)

Max Activating Token Index: 340

Text #15

Max Range: 1.8356. Min Range: -1.8356

Max Act: 1.0885. Min Act: -0.0000

Data Index: 1462434 (Python Code)

Max Activating Token Index: 708

Text #16

Max Range: 1.8356. Min Range: -1.8356

Max Act: 1.0850. Min Act: -0.0000

Data Index: 1181405 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 1.8356. Min Range: -1.8356

Max Act: 1.0263. Min Act: -0.0000

Data Index: 1084173 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 1.8356. Min Range: -1.8356

Max Act: 1.1057. Min Act: -0.0000

Data Index: 1394935 (Python Code)

Max Activating Token Index: 681

Text #19

Max Range: 1.8356. Min Range: -1.8356

Max Act: 1.0254. Min Act: -0.0000

Data Index: 1371760 (Python Code)

Max Activating Token Index: 959