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

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

Neuron 5763 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.9361. Min Act: -0.0000

Data Index: 923494 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.2860. Min Act: -0.0000

Data Index: 725126 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.2552. Min Act: -0.0000

Data Index: 1585991 (Python Code)

Max Activating Token Index: 485

Text #3

Max Range: 2.9361. Min Range: -2.9361

Max Act: 1.8711. Min Act: -0.0000

Data Index: 529065 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 2.9361. Min Range: -2.9361

Max Act: 1.8966. Min Act: -0.0000

Data Index: 1459022 (Python Code)

Max Activating Token Index: 112

Text #5

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.0565. Min Act: -0.0000

Data Index: 1617110 (Python Code)

Max Activating Token Index: 49

Text #6

Max Range: 2.9361. Min Range: -2.9361

Max Act: 1.7842. Min Act: -0.0000

Data Index: 1566692 (Python Code)

Max Activating Token Index: 184

Text #7

Max Range: 2.9361. Min Range: -2.9361

Max Act: 1.8918. Min Act: -0.0000

Data Index: 1424462 (Python Code)

Max Activating Token Index: 335

Text #8

Max Range: 2.9361. Min Range: -2.9361

Max Act: 1.8395. Min Act: -0.0000

Data Index: 1429566 (Python Code)

Max Activating Token Index: 145

Text #9

Max Range: 2.9361. Min Range: -2.9361

Max Act: 1.7160. Min Act: -0.0000

Data Index: 1454906 (Python Code)

Max Activating Token Index: 933

Text #10

Max Range: 2.9361. Min Range: -2.9361

Max Act: 1.9320. Min Act: -0.0000

Data Index: 177106 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 2.9361. Min Range: -2.9361

Max Act: 1.7232. Min Act: -0.0000

Data Index: 1430360 (Python Code)

Max Activating Token Index: 894

Text #12

Max Range: 2.9361. Min Range: -2.9361

Max Act: 1.8657. Min Act: -0.0000

Data Index: 1412050 (Python Code)

Max Activating Token Index: 77

Text #13

Max Range: 2.9361. Min Range: -2.9361

Max Act: 1.9199. Min Act: -0.0000

Data Index: 1497575 (Python Code)

Max Activating Token Index: 768

Text #14

Max Range: 2.9361. Min Range: -2.9361

Max Act: 1.8023. Min Act: -0.0000

Data Index: 1446986 (Python Code)

Max Activating Token Index: 919

Text #15

Max Range: 2.9361. Min Range: -2.9361

Max Act: 1.6576. Min Act: -0.0000

Data Index: 1529597 (Python Code)

Max Activating Token Index: 142

Text #16

Max Range: 2.9361. Min Range: -2.9361

Max Act: 1.6538. Min Act: -0.0000

Data Index: 1409275 (Python Code)

Max Activating Token Index: 780

Text #17

Max Range: 2.9361. Min Range: -2.9361

Max Act: 1.5598. Min Act: -0.0000

Data Index: 1403049 (Python Code)

Max Activating Token Index: 86

Text #18

Max Range: 2.9361. Min Range: -2.9361

Max Act: 1.4933. Min Act: -0.0000

Data Index: 1543401 (Python Code)

Max Activating Token Index: 610

Text #19

Max Range: 2.9361. Min Range: -2.9361

Max Act: 1.5135. Min Act: -0.0000

Data Index: 1445171 (Python Code)

Max Activating Token Index: 676