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

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

Neuron 2897 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.3576. Min Act: -0.0000

Data Index: 906106 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.3490. Min Act: -0.0000

Data Index: 1164476 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.3178. Min Act: -0.0001

Data Index: 57261 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.3005. Min Act: -0.0001

Data Index: 486269 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2929. Min Act: -0.0001

Data Index: 270714 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2945. Min Act: -0.0001

Data Index: 269208 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2893. Min Act: -0.0000

Data Index: 292100 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2914. Min Act: -0.0001

Data Index: 78973 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2738. Min Act: -0.0001

Data Index: 523861 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2911. Min Act: -0.0000

Data Index: 1100991 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2713. Min Act: -0.0000

Data Index: 1262367 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2795. Min Act: -0.0001

Data Index: 423641 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2400. Min Act: -0.0001

Data Index: 1218007 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2545. Min Act: -0.0000

Data Index: 3479 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2516. Min Act: -0.0001

Data Index: 1331466 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2504. Min Act: -0.0000

Data Index: 1254123 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2405. Min Act: -0.0001

Data Index: 100837 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2479. Min Act: -0.0000

Data Index: 443513 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2375. Min Act: -0.0001

Data Index: 24997 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2515. Min Act: -0.0001

Data Index: 958479 (C4 (Web Text))

Max Activating Token Index: 363