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

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

Neuron 3622 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2460. Min Range: -1.2460

Max Act: 1.2460. Min Act: -0.0001

Data Index: 59518 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.8875. Min Act: -0.0001

Data Index: 1348178 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.9050. Min Act: -0.0001

Data Index: 1492110 (Python Code)

Max Activating Token Index: 88

Text #3

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.8843. Min Act: -0.0001

Data Index: 376889 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.8006. Min Act: -0.0001

Data Index: 954090 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.8123. Min Act: -0.0001

Data Index: 176671 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.7478. Min Act: -0.0001

Data Index: 925784 (C4 (Web Text))

Max Activating Token Index: 674

Text #7

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.7924. Min Act: -0.0001

Data Index: 223979 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.7533. Min Act: -0.0001

Data Index: 249625 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.7506. Min Act: -0.0001

Data Index: 41667 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.7352. Min Act: -0.0001

Data Index: 1040216 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.7304. Min Act: -0.0001

Data Index: 309736 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.7791. Min Act: -0.0001

Data Index: 59639 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.7331. Min Act: -0.0000

Data Index: 1546364 (Python Code)

Max Activating Token Index: 701

Text #14

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.6793. Min Act: -0.0001

Data Index: 695881 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.7259. Min Act: -0.0001

Data Index: 1200521 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.6769. Min Act: -0.0001

Data Index: 939529 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.7389. Min Act: -0.0001

Data Index: 993264 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.7029. Min Act: -0.0001

Data Index: 662706 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.7013. Min Act: -0.0001

Data Index: 1461133 (Python Code)

Max Activating Token Index: 1017