Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1667 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.4285. Min Act: -0.0001

Data Index: 1441387 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3504. Min Act: -0.0001

Data Index: 541408 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.4121. Min Act: -0.0001

Data Index: 498838 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3044. Min Act: -0.0001

Data Index: 1207763 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2990. Min Act: -0.0001

Data Index: 772870 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2994. Min Act: -0.0001

Data Index: 1521670 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2936. Min Act: -0.0001

Data Index: 1381336 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3041. Min Act: -0.0001

Data Index: 916878 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2820. Min Act: -0.0001

Data Index: 1645252 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.1837. Min Act: -0.0001

Data Index: 1061569 (C4 (Web Text))

Max Activating Token Index: 491

Text #10

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2496. Min Act: -0.0001

Data Index: 1373461 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2483. Min Act: -0.0001

Data Index: 1366503 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2574. Min Act: -0.0001

Data Index: 1377530 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2528. Min Act: -0.0001

Data Index: 1378804 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2445. Min Act: -0.0001

Data Index: 329137 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.1841. Min Act: -0.0001

Data Index: 796038 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2377. Min Act: -0.0001

Data Index: 1407168 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2042. Min Act: -0.0001

Data Index: 218447 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2180. Min Act: -0.0001

Data Index: 1400975 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2382. Min Act: -0.0001

Data Index: 1479801 (Python Code)

Max Activating Token Index: 1023