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

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

Neuron 1609 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: 0.9916. Min Range: -0.9916

Max Act: 0.9916. Min Act: -0.0000

Data Index: 970400 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.9399. Min Act: -0.0000

Data Index: 930517 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.8383. Min Act: -0.0000

Data Index: 1049025 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.8551. Min Act: -0.0001

Data Index: 1153965 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.8325. Min Act: -0.0001

Data Index: 822556 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.8071. Min Act: -0.0000

Data Index: 11405 (C4 (Web Text))

Max Activating Token Index: 396

Text #6

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.8277. Min Act: -0.0000

Data Index: 216743 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.8000. Min Act: -0.0001

Data Index: 1025534 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.8026. Min Act: -0.0001

Data Index: 1136021 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.7676. Min Act: -0.0000

Data Index: 1354636 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.6966. Min Act: -0.0000

Data Index: 923917 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.7902. Min Act: -0.0000

Data Index: 895404 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.7394. Min Act: -0.0000

Data Index: 907949 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.7367. Min Act: -0.0000

Data Index: 864338 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.7562. Min Act: -0.0001

Data Index: 635280 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.7529. Min Act: -0.0000

Data Index: 246115 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.7019. Min Act: -0.0000

Data Index: 1306 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.7215. Min Act: -0.0000

Data Index: 379559 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.7421. Min Act: -0.0001

Data Index: 289276 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.7122. Min Act: -0.0001

Data Index: 1145298 (C4 (Web Text))

Max Activating Token Index: 99