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

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

Neuron 6012 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1992. Min Act: -0.0000

Data Index: 525049 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1877. Min Act: -0.0000

Data Index: 146961 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1800. Min Act: -0.0000

Data Index: 923065 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1637. Min Act: -0.0000

Data Index: 1215133 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1546. Min Act: -0.0000

Data Index: 1202983 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1497. Min Act: -0.0000

Data Index: 184241 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1584. Min Act: -0.0000

Data Index: 24763 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1432. Min Act: -0.0000

Data Index: 1050104 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1468. Min Act: -0.0000

Data Index: 620945 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1490. Min Act: -0.0000

Data Index: 347388 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1373. Min Act: -0.0000

Data Index: 1367858 (Python Code)

Max Activating Token Index: 323

Text #11

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1593. Min Act: -0.0000

Data Index: 708612 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1375. Min Act: -0.0000

Data Index: 1639873 (Python Code)

Max Activating Token Index: 699

Text #13

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1454. Min Act: -0.0000

Data Index: 318207 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1352. Min Act: -0.0000

Data Index: 1547327 (Python Code)

Max Activating Token Index: 128

Text #15

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1437. Min Act: -0.0000

Data Index: 1514567 (Python Code)

Max Activating Token Index: 127

Text #16

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1398. Min Act: -0.0000

Data Index: 1642162 (Python Code)

Max Activating Token Index: 232

Text #17

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1364. Min Act: -0.0000

Data Index: 1620088 (Python Code)

Max Activating Token Index: 144

Text #18

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1271. Min Act: -0.0000

Data Index: 1560387 (Python Code)

Max Activating Token Index: 274

Text #19

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1342. Min Act: -0.0000

Data Index: 4314 (C4 (Web Text))

Max Activating Token Index: 359