Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1266 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1944. Min Act: -0.0004

Data Index: 510777 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1914. Min Act: -0.0003

Data Index: 726403 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1710. Min Act: -0.0004

Data Index: 1136637 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1540. Min Act: -0.0004

Data Index: 525191 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1701. Min Act: -0.0003

Data Index: 1300747 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1669. Min Act: -0.0003

Data Index: 636984 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1558. Min Act: -0.0003

Data Index: 175169 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1703. Min Act: -0.0003

Data Index: 234166 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1509. Min Act: -0.0003

Data Index: 269158 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1535. Min Act: -0.0003

Data Index: 1278825 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1601. Min Act: -0.0004

Data Index: 91855 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1504. Min Act: -0.0003

Data Index: 946019 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1507. Min Act: -0.0004

Data Index: 1083070 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1532. Min Act: -0.0003

Data Index: 18915 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1549. Min Act: -0.0003

Data Index: 70173 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1566. Min Act: -0.0003

Data Index: 613281 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1455. Min Act: -0.0003

Data Index: 132730 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1560. Min Act: -0.0003

Data Index: 18124 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1522. Min Act: -0.0003

Data Index: 789237 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1431. Min Act: -0.0003

Data Index: 648251 (C4 (Web Text))

Max Activating Token Index: 388