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

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

Neuron 3806 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: 1.3026. Min Range: -1.3026

Max Act: 1.3026. Min Act: -0.0000

Data Index: 1133545 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 1.3026. Min Range: -1.3026

Max Act: 1.2936. Min Act: -0.0000

Data Index: 429680 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 1.3026. Min Range: -1.3026

Max Act: 1.2028. Min Act: -0.0000

Data Index: 794298 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 1.3026. Min Range: -1.3026

Max Act: 1.2335. Min Act: -0.0000

Data Index: 969243 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 1.3026. Min Range: -1.3026

Max Act: 1.1510. Min Act: -0.0000

Data Index: 209945 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 1.3026. Min Range: -1.3026

Max Act: 1.1393. Min Act: -0.0000

Data Index: 744821 (C4 (Web Text))

Max Activating Token Index: 410

Text #6

Max Range: 1.3026. Min Range: -1.3026

Max Act: 1.1328. Min Act: -0.0000

Data Index: 506814 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 1.3026. Min Range: -1.3026

Max Act: 1.0983. Min Act: -0.0000

Data Index: 189064 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 1.3026. Min Range: -1.3026

Max Act: 0.9100. Min Act: -0.0000

Data Index: 69280 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 1.3026. Min Range: -1.3026

Max Act: 0.8907. Min Act: -0.0000

Data Index: 1297176 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 1.3026. Min Range: -1.3026

Max Act: 0.8144. Min Act: -0.0000

Data Index: 1545808 (Python Code)

Max Activating Token Index: 132

Text #11

Max Range: 1.3026. Min Range: -1.3026

Max Act: 0.8340. Min Act: -0.0000

Data Index: 1268292 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 1.3026. Min Range: -1.3026

Max Act: 0.7181. Min Act: -0.0000

Data Index: 1296245 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 1.3026. Min Range: -1.3026

Max Act: 0.8110. Min Act: -0.0000

Data Index: 998275 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 1.3026. Min Range: -1.3026

Max Act: 0.7691. Min Act: -0.0000

Data Index: 1639917 (Python Code)

Max Activating Token Index: 979

Text #15

Max Range: 1.3026. Min Range: -1.3026

Max Act: 0.7655. Min Act: -0.0000

Data Index: 34509 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 1.3026. Min Range: -1.3026

Max Act: 0.7859. Min Act: -0.0000

Data Index: 742494 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 1.3026. Min Range: -1.3026

Max Act: 0.7576. Min Act: -0.0000

Data Index: 335551 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 1.3026. Min Range: -1.3026

Max Act: 0.7789. Min Act: -0.0000

Data Index: 331005 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 1.3026. Min Range: -1.3026

Max Act: 0.7197. Min Act: -0.0000

Data Index: 700049 (C4 (Web Text))

Max Activating Token Index: 725