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

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

Neuron 3646 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: 1.3458. Min Range: -1.3458

Max Act: 1.3446. Min Act: -0.0001

Data Index: 434546 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 1.3458. Min Range: -1.3458

Max Act: 1.3310. Min Act: -0.0001

Data Index: 1275261 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 1.3458. Min Range: -1.3458

Max Act: 1.3458. Min Act: -0.0000

Data Index: 929450 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 1.3458. Min Range: -1.3458

Max Act: 1.1407. Min Act: -0.0001

Data Index: 304479 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 1.3458. Min Range: -1.3458

Max Act: 1.1665. Min Act: -0.0001

Data Index: 30667 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 1.3458. Min Range: -1.3458

Max Act: 1.2152. Min Act: -0.0000

Data Index: 235251 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 1.3458. Min Range: -1.3458

Max Act: 1.1704. Min Act: -0.0001

Data Index: 1190979 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 1.3458. Min Range: -1.3458

Max Act: 1.1960. Min Act: -0.0000

Data Index: 170509 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 1.3458. Min Range: -1.3458

Max Act: 1.1827. Min Act: -0.0000

Data Index: 393725 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 1.3458. Min Range: -1.3458

Max Act: 1.2083. Min Act: -0.0001

Data Index: 510445 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 1.3458. Min Range: -1.3458

Max Act: 1.1225. Min Act: -0.0001

Data Index: 1119867 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 1.3458. Min Range: -1.3458

Max Act: 1.1749. Min Act: -0.0001

Data Index: 353865 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 1.3458. Min Range: -1.3458

Max Act: 1.0825. Min Act: -0.0001

Data Index: 21401 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 1.3458. Min Range: -1.3458

Max Act: 1.0679. Min Act: -0.0000

Data Index: 642819 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 1.3458. Min Range: -1.3458

Max Act: 1.0910. Min Act: -0.0001

Data Index: 838664 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 1.3458. Min Range: -1.3458

Max Act: 1.0883. Min Act: -0.0000

Data Index: 830825 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 1.3458. Min Range: -1.3458

Max Act: 1.0924. Min Act: -0.0001

Data Index: 1880 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 1.3458. Min Range: -1.3458

Max Act: 1.0529. Min Act: -0.0000

Data Index: 1234225 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 1.3458. Min Range: -1.3458

Max Act: 1.1178. Min Act: -0.0000

Data Index: 629529 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 1.3458. Min Range: -1.3458

Max Act: 1.1082. Min Act: -0.0000

Data Index: 470183 (C4 (Web Text))

Max Activating Token Index: 849