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

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

Neuron 681 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.9076. Min Act: -0.0000

Data Index: 1388309 (Python Code)

Max Activating Token Index: 431

Text #1

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.8559. Min Act: -0.0000

Data Index: 1586297 (Python Code)

Max Activating Token Index: 358

Text #2

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.8631. Min Act: -0.0000

Data Index: 1625256 (Python Code)

Max Activating Token Index: 7

Text #3

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.8773. Min Act: -0.0000

Data Index: 1122439 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.8432. Min Act: -0.0000

Data Index: 1428865 (Python Code)

Max Activating Token Index: 27

Text #5

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.7997. Min Act: -0.0000

Data Index: 1454467 (Python Code)

Max Activating Token Index: 235

Text #6

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.8801. Min Act: -0.0000

Data Index: 232660 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.7968. Min Act: -0.0000

Data Index: 1435612 (Python Code)

Max Activating Token Index: 170

Text #8

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.8164. Min Act: -0.0000

Data Index: 1390246 (Python Code)

Max Activating Token Index: 307

Text #9

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.8125. Min Act: -0.0000

Data Index: 964849 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.7364. Min Act: -0.0000

Data Index: 471122 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.7412. Min Act: -0.0000

Data Index: 339512 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.7629. Min Act: -0.0000

Data Index: 1650994 (Python Code)

Max Activating Token Index: 137

Text #13

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.7279. Min Act: -0.0000

Data Index: 1547293 (Python Code)

Max Activating Token Index: 114

Text #14

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.7343. Min Act: -0.0000

Data Index: 1627276 (Python Code)

Max Activating Token Index: 310

Text #15

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.6111. Min Act: -0.0000

Data Index: 870492 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.6470. Min Act: -0.0000

Data Index: 1557170 (Python Code)

Max Activating Token Index: 589

Text #17

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.6260. Min Act: -0.0000

Data Index: 1409905 (Python Code)

Max Activating Token Index: 991

Text #18

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.6479. Min Act: -0.0000

Data Index: 1529727 (Python Code)

Max Activating Token Index: 122

Text #19

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.6289. Min Act: -0.0000

Data Index: 1582532 (Python Code)

Max Activating Token Index: 220