Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2231 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0665. Min Act: -0.0003

Data Index: 1495916 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0656. Min Act: -0.0003

Data Index: 1444040 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0529. Min Act: -0.0003

Data Index: 1235920 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0549. Min Act: -0.0003

Data Index: 588322 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0506. Min Act: -0.0003

Data Index: 561238 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0463. Min Act: -0.0003

Data Index: 1385361 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0450. Min Act: -0.0003

Data Index: 1026792 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0445. Min Act: -0.0003

Data Index: 1474291 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0359. Min Act: -0.0003

Data Index: 509375 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0395. Min Act: -0.0003

Data Index: 1439362 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0532. Min Act: -0.0003

Data Index: 852569 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0417. Min Act: -0.0003

Data Index: 1394014 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0390. Min Act: -0.0003

Data Index: 862995 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0430. Min Act: -0.0003

Data Index: 1496514 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0435. Min Act: -0.0003

Data Index: 1608053 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0423. Min Act: -0.0003

Data Index: 1193317 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0389. Min Act: -0.0003

Data Index: 434882 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0398. Min Act: -0.0003

Data Index: 1596679 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0367. Min Act: -0.0003

Data Index: 1296944 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0353. Min Act: -0.0003

Data Index: 1143481 (C4 (Web Text))

Max Activating Token Index: 1023