Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3015 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.3937. Min Act: -0.0001

Data Index: 689718 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.4457. Min Act: -0.0001

Data Index: 352104 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.3615. Min Act: -0.0001

Data Index: 1118346 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.3368. Min Act: -0.0001

Data Index: 923195 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.3457. Min Act: -0.0001

Data Index: 1057398 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.3671. Min Act: -0.0000

Data Index: 926048 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.3530. Min Act: -0.0000

Data Index: 249713 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.3445. Min Act: -0.0001

Data Index: 1203832 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.3290. Min Act: -0.0000

Data Index: 706688 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.3355. Min Act: -0.0001

Data Index: 1154281 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.3281. Min Act: -0.0000

Data Index: 408334 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.3244. Min Act: -0.0001

Data Index: 1352346 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.3107. Min Act: -0.0001

Data Index: 90848 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.3029. Min Act: -0.0001

Data Index: 1178312 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.2767. Min Act: -0.0001

Data Index: 1309125 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.2997. Min Act: -0.0001

Data Index: 1226563 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.2782. Min Act: -0.0000

Data Index: 638282 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.2741. Min Act: -0.0001

Data Index: 1348468 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.2801. Min Act: -0.0001

Data Index: 636944 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.2708. Min Act: -0.0000

Data Index: 875706 (C4 (Web Text))

Max Activating Token Index: 235