Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4421 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4508. Min Range: -2.4508

Max Act: 2.4508. Min Act: -0.0000

Data Index: 1475842 (Python Code)

Max Activating Token Index: 437

Text #1

Max Range: 2.4508. Min Range: -2.4508

Max Act: 1.9768. Min Act: -0.0000

Data Index: 1578483 (Python Code)

Max Activating Token Index: 167

Text #2

Max Range: 2.4508. Min Range: -2.4508

Max Act: 2.0779. Min Act: -0.0000

Data Index: 882805 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 2.4508. Min Range: -2.4508

Max Act: 2.0585. Min Act: -0.0000

Data Index: 1521313 (Python Code)

Max Activating Token Index: 201

Text #4

Max Range: 2.4508. Min Range: -2.4508

Max Act: 2.2864. Min Act: -0.0000

Data Index: 638868 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 2.4508. Min Range: -2.4508

Max Act: 2.0578. Min Act: -0.0000

Data Index: 1534380 (Python Code)

Max Activating Token Index: 616

Text #6

Max Range: 2.4508. Min Range: -2.4508

Max Act: 1.8603. Min Act: -0.0000

Data Index: 1608601 (Python Code)

Max Activating Token Index: 304

Text #7

Max Range: 2.4508. Min Range: -2.4508

Max Act: 1.9675. Min Act: -0.0000

Data Index: 210640 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 2.4508. Min Range: -2.4508

Max Act: 1.9354. Min Act: -0.0000

Data Index: 1648553 (Python Code)

Max Activating Token Index: 399

Text #9

Max Range: 2.4508. Min Range: -2.4508

Max Act: 1.9468. Min Act: -0.0000

Data Index: 683733 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 2.4508. Min Range: -2.4508

Max Act: 1.9317. Min Act: -0.0000

Data Index: 780114 (C4 (Web Text))

Max Activating Token Index: 338

Text #11

Max Range: 2.4508. Min Range: -2.4508

Max Act: 2.0208. Min Act: -0.0000

Data Index: 1040204 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 2.4508. Min Range: -2.4508

Max Act: 1.9120. Min Act: -0.0000

Data Index: 623897 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 2.4508. Min Range: -2.4508

Max Act: 1.9070. Min Act: -0.0000

Data Index: 471783 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 2.4508. Min Range: -2.4508

Max Act: 2.0057. Min Act: -0.0000

Data Index: 1352899 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 2.4508. Min Range: -2.4508

Max Act: 1.9193. Min Act: -0.0000

Data Index: 1457797 (Python Code)

Max Activating Token Index: 325

Text #16

Max Range: 2.4508. Min Range: -2.4508

Max Act: 1.7183. Min Act: -0.0000

Data Index: 1467984 (Python Code)

Max Activating Token Index: 616

Text #17

Max Range: 2.4508. Min Range: -2.4508

Max Act: 1.7292. Min Act: -0.0000

Data Index: 838561 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 2.4508. Min Range: -2.4508

Max Act: 1.7944. Min Act: -0.0000

Data Index: 298770 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 2.4508. Min Range: -2.4508

Max Act: 1.7957. Min Act: -0.0000

Data Index: 979922 (C4 (Web Text))

Max Activating Token Index: 448