Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 971 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.9035. Min Act: -0.0000

Data Index: 365855 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.8549. Min Act: -0.0000

Data Index: 52855 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.8912. Min Act: -0.0000

Data Index: 675852 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.8296. Min Act: -0.0000

Data Index: 1118574 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6924. Min Act: -0.0000

Data Index: 511672 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.7853. Min Act: -0.0000

Data Index: 787127 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.7276. Min Act: -0.0000

Data Index: 1012695 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.7455. Min Act: -0.0000

Data Index: 1246751 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.7511. Min Act: -0.0000

Data Index: 1301723 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.7021. Min Act: -0.0000

Data Index: 190868 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6755. Min Act: -0.0000

Data Index: 66115 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.7012. Min Act: 0.0000

Data Index: 929343 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6352. Min Act: -0.0000

Data Index: 1008358 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6322. Min Act: -0.0000

Data Index: 637984 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.5907. Min Act: -0.0000

Data Index: 285096 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.5997. Min Act: -0.0000

Data Index: 747308 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6439. Min Act: -0.0000

Data Index: 498703 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6353. Min Act: -0.0000

Data Index: 272802 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6424. Min Act: -0.0000

Data Index: 442501 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6342. Min Act: -0.0000

Data Index: 527741 (C4 (Web Text))

Max Activating Token Index: 466