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

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

Neuron 1565 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0766. Min Act: -0.0002

Data Index: 645755 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0416. Min Act: -0.0002

Data Index: 981008 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0397. Min Act: -0.0002

Data Index: 660989 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0384. Min Act: -0.0002

Data Index: 40831 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0367. Min Act: -0.0002

Data Index: 1375346 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0359. Min Act: -0.0002

Data Index: 635697 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0347. Min Act: -0.0002

Data Index: 1023880 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1586008 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0335. Min Act: -0.0002

Data Index: 1233441 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0331. Min Act: -0.0002

Data Index: 814025 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0323. Min Act: -0.0001

Data Index: 165480 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0320. Min Act: -0.0002

Data Index: 866634 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0319. Min Act: -0.0002

Data Index: 1427752 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0312. Min Act: -0.0002

Data Index: 1008935 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0309. Min Act: -0.0002

Data Index: 1511714 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1126065 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0302. Min Act: -0.0002

Data Index: 327853 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0306. Min Act: -0.0001

Data Index: 1634112 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0306. Min Act: -0.0002

Data Index: 242842 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0303. Min Act: -0.0002

Data Index: 131160 (C4 (Web Text))

Max Activating Token Index: 58