Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 888 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.7171. Min Act: -0.0004

Data Index: 1573600 (Python Code)

Max Activating Token Index: 494

Text #1

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.7100. Min Act: -0.0004

Data Index: 1617746 (Python Code)

Max Activating Token Index: 588

Text #2

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.6475. Min Act: -0.0004

Data Index: 1583079 (Python Code)

Max Activating Token Index: 213

Text #3

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.6264. Min Act: -0.0004

Data Index: 1422763 (Python Code)

Max Activating Token Index: 919

Text #4

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.6232. Min Act: -0.0004

Data Index: 1626730 (Python Code)

Max Activating Token Index: 144

Text #5

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.6232. Min Act: -0.0004

Data Index: 1423362 (Python Code)

Max Activating Token Index: 144

Text #6

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.6628. Min Act: -0.0004

Data Index: 1409977 (Python Code)

Max Activating Token Index: 126

Text #7

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.6741. Min Act: -0.0004

Data Index: 1466526 (Python Code)

Max Activating Token Index: 193

Text #8

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.6668. Min Act: -0.0004

Data Index: 1524110 (Python Code)

Max Activating Token Index: 390

Text #9

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.6465. Min Act: -0.0004

Data Index: 1577295 (Python Code)

Max Activating Token Index: 147

Text #10

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.5782. Min Act: -0.0004

Data Index: 1653323 (Python Code)

Max Activating Token Index: 824

Text #11

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.6519. Min Act: -0.0004

Data Index: 1447136 (Python Code)

Max Activating Token Index: 188

Text #12

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.6254. Min Act: -0.0004

Data Index: 1459068 (Python Code)

Max Activating Token Index: 472

Text #13

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.6202. Min Act: -0.0004

Data Index: 1504231 (Python Code)

Max Activating Token Index: 443

Text #14

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.5980. Min Act: -0.0004

Data Index: 1399796 (Python Code)

Max Activating Token Index: 351

Text #15

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.5756. Min Act: -0.0004

Data Index: 1558742 (Python Code)

Max Activating Token Index: 771

Text #16

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.6286. Min Act: -0.0004

Data Index: 1519569 (Python Code)

Max Activating Token Index: 304

Text #17

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.6036. Min Act: -0.0004

Data Index: 1439216 (Python Code)

Max Activating Token Index: 999

Text #18

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.5875. Min Act: -0.0004

Data Index: 1502577 (Python Code)

Max Activating Token Index: 699

Text #19

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.6206. Min Act: -0.0004

Data Index: 1482539 (Python Code)

Max Activating Token Index: 99