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

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

Neuron 2652 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: 1.4294. Min Range: -1.4294

Max Act: 1.4294. Min Act: -0.0000

Data Index: 470028 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 1.4294. Min Range: -1.4294

Max Act: 1.3898. Min Act: -0.0000

Data Index: 419520 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 1.4294. Min Range: -1.4294

Max Act: 1.4258. Min Act: -0.0000

Data Index: 13274 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 1.4294. Min Range: -1.4294

Max Act: 1.3334. Min Act: -0.0000

Data Index: 1034881 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 1.4294. Min Range: -1.4294

Max Act: 1.1751. Min Act: -0.0000

Data Index: 281807 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 1.4294. Min Range: -1.4294

Max Act: 1.2464. Min Act: -0.0000

Data Index: 199905 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 1.4294. Min Range: -1.4294

Max Act: 1.2441. Min Act: -0.0000

Data Index: 655270 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 1.4294. Min Range: -1.4294

Max Act: 1.1457. Min Act: -0.0000

Data Index: 277478 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 1.4294. Min Range: -1.4294

Max Act: 1.2118. Min Act: -0.0000

Data Index: 740302 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 1.4294. Min Range: -1.4294

Max Act: 1.1191. Min Act: -0.0000

Data Index: 145591 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 1.4294. Min Range: -1.4294

Max Act: 1.1836. Min Act: -0.0000

Data Index: 714743 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 1.4294. Min Range: -1.4294

Max Act: 1.1162. Min Act: -0.0000

Data Index: 1133786 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 1.4294. Min Range: -1.4294

Max Act: 1.1498. Min Act: -0.0000

Data Index: 1222426 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 1.4294. Min Range: -1.4294

Max Act: 1.0638. Min Act: -0.0000

Data Index: 451612 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 1.4294. Min Range: -1.4294

Max Act: 1.0984. Min Act: -0.0000

Data Index: 134067 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 1.4294. Min Range: -1.4294

Max Act: 1.1506. Min Act: -0.0000

Data Index: 68520 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 1.4294. Min Range: -1.4294

Max Act: 1.0636. Min Act: -0.0000

Data Index: 762178 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 1.4294. Min Range: -1.4294

Max Act: 1.0475. Min Act: -0.0000

Data Index: 1147622 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 1.4294. Min Range: -1.4294

Max Act: 1.0352. Min Act: -0.0000

Data Index: 1222517 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 1.4294. Min Range: -1.4294

Max Act: 0.9580. Min Act: -0.0000

Data Index: 417306 (C4 (Web Text))

Max Activating Token Index: 717