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

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

Neuron 1049 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: 2.4716. Min Range: -2.4716

Max Act: 2.4716. Min Act: -0.0000

Data Index: 1462848 (Python Code)

Max Activating Token Index: 100

Text #1

Max Range: 2.4716. Min Range: -2.4716

Max Act: 0.9478. Min Act: -0.0000

Data Index: 548292 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 2.4716. Min Range: -2.4716

Max Act: 0.9105. Min Act: -0.0000

Data Index: 1419042 (Python Code)

Max Activating Token Index: 643

Text #3

Max Range: 2.4716. Min Range: -2.4716

Max Act: 0.8138. Min Act: -0.0000

Data Index: 1585257 (Python Code)

Max Activating Token Index: 504

Text #4

Max Range: 2.4716. Min Range: -2.4716

Max Act: 0.9443. Min Act: -0.0000

Data Index: 1249710 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 2.4716. Min Range: -2.4716

Max Act: 0.8481. Min Act: -0.0000

Data Index: 99336 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 2.4716. Min Range: -2.4716

Max Act: 0.8723. Min Act: -0.0000

Data Index: 1378276 (Python Code)

Max Activating Token Index: 158

Text #7

Max Range: 2.4716. Min Range: -2.4716

Max Act: 0.8483. Min Act: -0.0000

Data Index: 935198 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 2.4716. Min Range: -2.4716

Max Act: 0.8404. Min Act: -0.0000

Data Index: 342381 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 2.4716. Min Range: -2.4716

Max Act: 0.8912. Min Act: -0.0000

Data Index: 1335360 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 2.4716. Min Range: -2.4716

Max Act: 0.8876. Min Act: -0.0000

Data Index: 1076102 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 2.4716. Min Range: -2.4716

Max Act: 0.8076. Min Act: -0.0000

Data Index: 1593676 (Python Code)

Max Activating Token Index: 856

Text #12

Max Range: 2.4716. Min Range: -2.4716

Max Act: 0.8571. Min Act: -0.0000

Data Index: 134927 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 2.4716. Min Range: -2.4716

Max Act: 0.7771. Min Act: -0.0000

Data Index: 1080668 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 2.4716. Min Range: -2.4716

Max Act: 0.8758. Min Act: -0.0000

Data Index: 368287 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 2.4716. Min Range: -2.4716

Max Act: 0.7773. Min Act: -0.0000

Data Index: 1606796 (Python Code)

Max Activating Token Index: 44

Text #16

Max Range: 2.4716. Min Range: -2.4716

Max Act: 0.7618. Min Act: -0.0000

Data Index: 629867 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 2.4716. Min Range: -2.4716

Max Act: 0.7327. Min Act: -0.0000

Data Index: 470635 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 2.4716. Min Range: -2.4716

Max Act: 0.7424. Min Act: -0.0000

Data Index: 1372805 (Python Code)

Max Activating Token Index: 979

Text #19

Max Range: 2.4716. Min Range: -2.4716

Max Act: 0.8094. Min Act: -0.0000

Data Index: 1280556 (C4 (Web Text))

Max Activating Token Index: 180