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

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

Neuron 675 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.7934. Min Act: 0.0000

Data Index: 1191802 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.8083. Min Act: -0.0000

Data Index: 51870 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.7830. Min Act: -0.0000

Data Index: 974775 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.7269. Min Act: 0.0000

Data Index: 521510 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.7224. Min Act: -0.0000

Data Index: 1274604 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.7059. Min Act: -0.0000

Data Index: 736768 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.7469. Min Act: -0.0000

Data Index: 909540 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.7179. Min Act: -0.0000

Data Index: 227242 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6972. Min Act: 0.0000

Data Index: 606206 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6790. Min Act: -0.0000

Data Index: 1219622 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6803. Min Act: -0.0000

Data Index: 974283 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6979. Min Act: -0.0000

Data Index: 311299 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6970. Min Act: 0.0000

Data Index: 942945 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6578. Min Act: 0.0000

Data Index: 1239831 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6274. Min Act: -0.0000

Data Index: 1233942 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6311. Min Act: -0.0000

Data Index: 483139 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6513. Min Act: -0.0000

Data Index: 396763 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6907. Min Act: -0.0000

Data Index: 601292 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6926. Min Act: -0.0000

Data Index: 1332528 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6686. Min Act: -0.0000

Data Index: 1353440 (C4 (Web Text))

Max Activating Token Index: 149