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

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

Neuron 2177 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4678. Min Range: -0.4678

Max Act: 0.4527. Min Act: -0.0001

Data Index: 1510926 (Python Code)

Max Activating Token Index: 347

Text #1

Max Range: 0.4678. Min Range: -0.4678

Max Act: 0.4678. Min Act: -0.0000

Data Index: 1612654 (Python Code)

Max Activating Token Index: 213

Text #2

Max Range: 0.4678. Min Range: -0.4678

Max Act: 0.4054. Min Act: -0.0000

Data Index: 1365848 (Python Code)

Max Activating Token Index: 210

Text #3

Max Range: 0.4678. Min Range: -0.4678

Max Act: 0.3678. Min Act: -0.0001

Data Index: 1480935 (Python Code)

Max Activating Token Index: 810

Text #4

Max Range: 0.4678. Min Range: -0.4678

Max Act: 0.4019. Min Act: -0.0000

Data Index: 1369244 (Python Code)

Max Activating Token Index: 280

Text #5

Max Range: 0.4678. Min Range: -0.4678

Max Act: 0.4263. Min Act: -0.0000

Data Index: 1596315 (Python Code)

Max Activating Token Index: 191

Text #6

Max Range: 0.4678. Min Range: -0.4678

Max Act: 0.3658. Min Act: -0.0000

Data Index: 1357127 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 0.4678. Min Range: -0.4678

Max Act: 0.3280. Min Act: -0.0000

Data Index: 478805 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 0.4678. Min Range: -0.4678

Max Act: 0.3427. Min Act: -0.0000

Data Index: 455770 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 0.4678. Min Range: -0.4678

Max Act: 0.3275. Min Act: -0.0000

Data Index: 323670 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 0.4678. Min Range: -0.4678

Max Act: 0.3103. Min Act: -0.0000

Data Index: 1638310 (Python Code)

Max Activating Token Index: 584

Text #11

Max Range: 0.4678. Min Range: -0.4678

Max Act: 0.3017. Min Act: -0.0000

Data Index: 346901 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.4678. Min Range: -0.4678

Max Act: 0.3054. Min Act: -0.0000

Data Index: 64275 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.4678. Min Range: -0.4678

Max Act: 0.3027. Min Act: -0.0000

Data Index: 914805 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 0.4678. Min Range: -0.4678

Max Act: 0.2996. Min Act: -0.0001

Data Index: 1466102 (Python Code)

Max Activating Token Index: 498

Text #15

Max Range: 0.4678. Min Range: -0.4678

Max Act: 0.3125. Min Act: -0.0001

Data Index: 1174299 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 0.4678. Min Range: -0.4678

Max Act: 0.2945. Min Act: -0.0000

Data Index: 75642 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 0.4678. Min Range: -0.4678

Max Act: 0.3030. Min Act: -0.0001

Data Index: 1589285 (Python Code)

Max Activating Token Index: 52

Text #18

Max Range: 0.4678. Min Range: -0.4678

Max Act: 0.3137. Min Act: -0.0000

Data Index: 2254 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 0.4678. Min Range: -0.4678

Max Act: 0.2863. Min Act: -0.0000

Data Index: 917406 (C4 (Web Text))

Max Activating Token Index: 65