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

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

Neuron 597 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.6485. Min Act: -0.0000

Data Index: 406017 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.4899. Min Act: -0.0001

Data Index: 1495539 (Python Code)

Max Activating Token Index: 1008

Text #2

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.5862. Min Act: -0.0000

Data Index: 1242258 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.4534. Min Act: -0.0000

Data Index: 558994 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.1211. Min Act: -0.0000

Data Index: 748114 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.1692. Min Act: -0.0001

Data Index: 92942 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.1675. Min Act: -0.0000

Data Index: 27167 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.0572. Min Act: -0.0000

Data Index: 767217 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.1168. Min Act: -0.0001

Data Index: 1085306 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.0353. Min Act: -0.0001

Data Index: 834891 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.0705. Min Act: -0.0001

Data Index: 1377117 (Python Code)

Max Activating Token Index: 980

Text #11

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.0828. Min Act: -0.0001

Data Index: 1437518 (Python Code)

Max Activating Token Index: 200

Text #12

Max Range: 1.6485. Min Range: -1.6485

Max Act: 0.9948. Min Act: -0.0001

Data Index: 205419 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.0223. Min Act: -0.0001

Data Index: 800721 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.0428. Min Act: -0.0001

Data Index: 164877 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.0476. Min Act: -0.0001

Data Index: 745683 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.0550. Min Act: -0.0001

Data Index: 881314 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.0185. Min Act: -0.0000

Data Index: 686663 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 1.6485. Min Range: -1.6485

Max Act: 0.9237. Min Act: -0.0000

Data Index: 895846 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 1.6485. Min Range: -1.6485

Max Act: 0.9951. Min Act: -0.0001

Data Index: 331377 (C4 (Web Text))

Max Activating Token Index: 711