Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4975 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.8519. Min Range: -3.8519

Max Act: 3.7907. Min Act: -0.0000

Data Index: 938418 (C4 (Web Text))

Max Activating Token Index: 269

Text #1

Max Range: 3.8519. Min Range: -3.8519

Max Act: 3.8356. Min Act: -0.0000

Data Index: 650123 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 3.8519. Min Range: -3.8519

Max Act: 3.7542. Min Act: -0.0000

Data Index: 415332 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 3.8519. Min Range: -3.8519

Max Act: 3.8519. Min Act: -0.0000

Data Index: 1052406 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 3.8519. Min Range: -3.8519

Max Act: 3.4705. Min Act: -0.0000

Data Index: 502863 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 3.8519. Min Range: -3.8519

Max Act: 3.5348. Min Act: -0.0000

Data Index: 1212474 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 3.8519. Min Range: -3.8519

Max Act: 3.5574. Min Act: -0.0000

Data Index: 1314329 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 3.8519. Min Range: -3.8519

Max Act: 3.3767. Min Act: -0.0000

Data Index: 628297 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 3.8519. Min Range: -3.8519

Max Act: 3.2087. Min Act: -0.0000

Data Index: 106515 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 3.8519. Min Range: -3.8519

Max Act: 3.3397. Min Act: -0.0000

Data Index: 891218 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 3.8519. Min Range: -3.8519

Max Act: 3.4697. Min Act: -0.0000

Data Index: 661557 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 3.8519. Min Range: -3.8519

Max Act: 3.2763. Min Act: -0.0000

Data Index: 426620 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 3.8519. Min Range: -3.8519

Max Act: 3.2466. Min Act: -0.0000

Data Index: 654001 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 3.8519. Min Range: -3.8519

Max Act: 3.1035. Min Act: -0.0000

Data Index: 373062 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 3.8519. Min Range: -3.8519

Max Act: 3.0698. Min Act: -0.0000

Data Index: 259175 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 3.8519. Min Range: -3.8519

Max Act: 3.2163. Min Act: -0.0000

Data Index: 644262 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 3.8519. Min Range: -3.8519

Max Act: 2.9900. Min Act: -0.0000

Data Index: 101356 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 3.8519. Min Range: -3.8519

Max Act: 3.1330. Min Act: -0.0000

Data Index: 629161 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 3.8519. Min Range: -3.8519

Max Act: 3.2506. Min Act: -0.0000

Data Index: 908774 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 3.8519. Min Range: -3.8519

Max Act: 2.9459. Min Act: -0.0000

Data Index: 1295769 (C4 (Web Text))

Max Activating Token Index: 677