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

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

Neuron 871 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1323. Min Range: -2.1323

Max Act: 2.1323. Min Act: -0.0000

Data Index: 1335302 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.9930. Min Act: -0.0000

Data Index: 156590 (C4 (Web Text))

Max Activating Token Index: 334

Text #2

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.6780. Min Act: -0.0000

Data Index: 1389551 (Python Code)

Max Activating Token Index: 102

Text #3

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.6394. Min Act: -0.0000

Data Index: 1280572 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.7100. Min Act: -0.0000

Data Index: 605942 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.6724. Min Act: -0.0000

Data Index: 735087 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.6148. Min Act: -0.0000

Data Index: 154135 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.6052. Min Act: -0.0000

Data Index: 842441 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.6930. Min Act: -0.0000

Data Index: 52093 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.5135. Min Act: -0.0000

Data Index: 762478 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.4574. Min Act: -0.0000

Data Index: 1172084 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.5208. Min Act: -0.0000

Data Index: 295016 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.5646. Min Act: -0.0000

Data Index: 48862 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.5052. Min Act: -0.0000

Data Index: 256223 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.5401. Min Act: -0.0000

Data Index: 1067551 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.3675. Min Act: -0.0000

Data Index: 66552 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.3741. Min Act: -0.0000

Data Index: 571218 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.4030. Min Act: -0.0000

Data Index: 294214 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.4416. Min Act: -0.0000

Data Index: 1126358 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.3423. Min Act: -0.0000

Data Index: 981006 (C4 (Web Text))

Max Activating Token Index: 785