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

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

Neuron 2660 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.7545. Min Act: -0.0001

Data Index: 678493 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.4757. Min Act: -0.0001

Data Index: 1579915 (Python Code)

Max Activating Token Index: 884

Text #2

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.5703. Min Act: -0.0000

Data Index: 1404868 (Python Code)

Max Activating Token Index: 28

Text #3

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.6288. Min Act: -0.0001

Data Index: 1372022 (Python Code)

Max Activating Token Index: 694

Text #4

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.4187. Min Act: -0.0001

Data Index: 1520721 (Python Code)

Max Activating Token Index: 197

Text #5

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.3867. Min Act: -0.0000

Data Index: 1543836 (Python Code)

Max Activating Token Index: 488

Text #6

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.3467. Min Act: -0.0000

Data Index: 1583262 (Python Code)

Max Activating Token Index: 253

Text #7

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.4591. Min Act: -0.0001

Data Index: 1455060 (Python Code)

Max Activating Token Index: 153

Text #8

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.4668. Min Act: -0.0001

Data Index: 1626930 (Python Code)

Max Activating Token Index: 907

Text #9

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.0901. Min Act: -0.0001

Data Index: 1502995 (Python Code)

Max Activating Token Index: 99

Text #10

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.0973. Min Act: -0.0001

Data Index: 635416 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.1794. Min Act: -0.0000

Data Index: 1494602 (Python Code)

Max Activating Token Index: 798

Text #12

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.1218. Min Act: -0.0001

Data Index: 1651371 (Python Code)

Max Activating Token Index: 514

Text #13

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.1226. Min Act: -0.0000

Data Index: 1555010 (Python Code)

Max Activating Token Index: 264

Text #14

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.0956. Min Act: -0.0000

Data Index: 226884 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.0974. Min Act: -0.0000

Data Index: 1463041 (Python Code)

Max Activating Token Index: 122

Text #16

Max Range: 1.7545. Min Range: -1.7545

Max Act: 0.9413. Min Act: -0.0001

Data Index: 456434 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 1.7545. Min Range: -1.7545

Max Act: 0.9881. Min Act: -0.0000

Data Index: 1655709 (Python Code)

Max Activating Token Index: 34

Text #18

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.0583. Min Act: -0.0001

Data Index: 1542248 (Python Code)

Max Activating Token Index: 767

Text #19

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.0314. Min Act: -0.0001

Data Index: 1409622 (Python Code)

Max Activating Token Index: 190