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

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

Neuron 2173 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3026. Min Range: -1.3026

Max Act: 1.3026. Min Act: -0.0001

Data Index: 2602 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 1.3026. Min Range: -1.3026

Max Act: 1.1854. Min Act: -0.0001

Data Index: 76271 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 1.3026. Min Range: -1.3026

Max Act: 1.1433. Min Act: -0.0001

Data Index: 1538415 (Python Code)

Max Activating Token Index: 678

Text #3

Max Range: 1.3026. Min Range: -1.3026

Max Act: 1.1692. Min Act: -0.0001

Data Index: 188980 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 1.3026. Min Range: -1.3026

Max Act: 1.0897. Min Act: -0.0001

Data Index: 62413 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 1.3026. Min Range: -1.3026

Max Act: 1.0281. Min Act: -0.0001

Data Index: 1247143 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 1.3026. Min Range: -1.3026

Max Act: 1.0430. Min Act: -0.0001

Data Index: 1383969 (Python Code)

Max Activating Token Index: 981

Text #7

Max Range: 1.3026. Min Range: -1.3026

Max Act: 0.9393. Min Act: -0.0001

Data Index: 182569 (C4 (Web Text))

Max Activating Token Index: 974

Text #8

Max Range: 1.3026. Min Range: -1.3026

Max Act: 1.0014. Min Act: -0.0001

Data Index: 1434093 (Python Code)

Max Activating Token Index: 64

Text #9

Max Range: 1.3026. Min Range: -1.3026

Max Act: 0.9691. Min Act: -0.0001

Data Index: 1264994 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 1.3026. Min Range: -1.3026

Max Act: 1.0029. Min Act: -0.0001

Data Index: 1406959 (Python Code)

Max Activating Token Index: 121

Text #11

Max Range: 1.3026. Min Range: -1.3026

Max Act: 1.0555. Min Act: -0.0001

Data Index: 1135405 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 1.3026. Min Range: -1.3026

Max Act: 1.0513. Min Act: -0.0001

Data Index: 1425135 (Python Code)

Max Activating Token Index: 960

Text #13

Max Range: 1.3026. Min Range: -1.3026

Max Act: 1.1088. Min Act: -0.0001

Data Index: 903771 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 1.3026. Min Range: -1.3026

Max Act: 1.0034. Min Act: -0.0001

Data Index: 242323 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 1.3026. Min Range: -1.3026

Max Act: 0.9693. Min Act: -0.0001

Data Index: 930553 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 1.3026. Min Range: -1.3026

Max Act: 0.9910. Min Act: -0.0001

Data Index: 848213 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 1.3026. Min Range: -1.3026

Max Act: 0.9565. Min Act: -0.0001

Data Index: 1276744 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 1.3026. Min Range: -1.3026

Max Act: 0.9791. Min Act: -0.0001

Data Index: 553781 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 1.3026. Min Range: -1.3026

Max Act: 1.0481. Min Act: -0.0001

Data Index: 833871 (C4 (Web Text))

Max Activating Token Index: 308