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

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

Neuron 2257 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: 2.4109. Min Range: -2.4109

Max Act: 2.3329. Min Act: -0.0000

Data Index: 1599573 (Python Code)

Max Activating Token Index: 86

Text #1

Max Range: 2.4109. Min Range: -2.4109

Max Act: 2.4109. Min Act: -0.0000

Data Index: 1416873 (Python Code)

Max Activating Token Index: 845

Text #2

Max Range: 2.4109. Min Range: -2.4109

Max Act: 1.9628. Min Act: -0.0000

Data Index: 1643781 (Python Code)

Max Activating Token Index: 102

Text #3

Max Range: 2.4109. Min Range: -2.4109

Max Act: 1.9423. Min Act: -0.0000

Data Index: 1428441 (Python Code)

Max Activating Token Index: 389

Text #4

Max Range: 2.4109. Min Range: -2.4109

Max Act: 1.9496. Min Act: -0.0000

Data Index: 1419995 (Python Code)

Max Activating Token Index: 640

Text #5

Max Range: 2.4109. Min Range: -2.4109

Max Act: 1.8286. Min Act: -0.0000

Data Index: 1368298 (Python Code)

Max Activating Token Index: 954

Text #6

Max Range: 2.4109. Min Range: -2.4109

Max Act: 1.7493. Min Act: -0.0000

Data Index: 1415725 (Python Code)

Max Activating Token Index: 830

Text #7

Max Range: 2.4109. Min Range: -2.4109

Max Act: 1.6836. Min Act: -0.0000

Data Index: 1563881 (Python Code)

Max Activating Token Index: 201

Text #8

Max Range: 2.4109. Min Range: -2.4109

Max Act: 1.9119. Min Act: -0.0000

Data Index: 1580775 (Python Code)

Max Activating Token Index: 77

Text #9

Max Range: 2.4109. Min Range: -2.4109

Max Act: 1.8580. Min Act: -0.0000

Data Index: 1521493 (Python Code)

Max Activating Token Index: 376

Text #10

Max Range: 2.4109. Min Range: -2.4109

Max Act: 1.7545. Min Act: -0.0000

Data Index: 1455027 (Python Code)

Max Activating Token Index: 308

Text #11

Max Range: 2.4109. Min Range: -2.4109

Max Act: 1.8363. Min Act: -0.0000

Data Index: 1575280 (Python Code)

Max Activating Token Index: 681

Text #12

Max Range: 2.4109. Min Range: -2.4109

Max Act: 1.7339. Min Act: -0.0000

Data Index: 1432444 (Python Code)

Max Activating Token Index: 98

Text #13

Max Range: 2.4109. Min Range: -2.4109

Max Act: 1.8166. Min Act: -0.0000

Data Index: 1612091 (Python Code)

Max Activating Token Index: 389

Text #14

Max Range: 2.4109. Min Range: -2.4109

Max Act: 1.7118. Min Act: -0.0000

Data Index: 1513690 (Python Code)

Max Activating Token Index: 269

Text #15

Max Range: 2.4109. Min Range: -2.4109

Max Act: 1.7033. Min Act: -0.0000

Data Index: 1455631 (Python Code)

Max Activating Token Index: 49

Text #16

Max Range: 2.4109. Min Range: -2.4109

Max Act: 1.6516. Min Act: -0.0000

Data Index: 1398414 (Python Code)

Max Activating Token Index: 379

Text #17

Max Range: 2.4109. Min Range: -2.4109

Max Act: 1.7488. Min Act: -0.0000

Data Index: 1370342 (Python Code)

Max Activating Token Index: 150

Text #18

Max Range: 2.4109. Min Range: -2.4109

Max Act: 1.6733. Min Act: -0.0000

Data Index: 1622921 (Python Code)

Max Activating Token Index: 281

Text #19

Max Range: 2.4109. Min Range: -2.4109

Max Act: 1.7533. Min Act: -0.0000

Data Index: 1375192 (Python Code)

Max Activating Token Index: 920