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

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

Neuron 5034 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: 3.0203. Min Range: -3.0203

Max Act: 3.0203. Min Act: -0.0000

Data Index: 1388331 (Python Code)

Max Activating Token Index: 172

Text #1

Max Range: 3.0203. Min Range: -3.0203

Max Act: 2.9727. Min Act: -0.0000

Data Index: 1595067 (Python Code)

Max Activating Token Index: 985

Text #2

Max Range: 3.0203. Min Range: -3.0203

Max Act: 2.5369. Min Act: -0.0000

Data Index: 1604333 (Python Code)

Max Activating Token Index: 141

Text #3

Max Range: 3.0203. Min Range: -3.0203

Max Act: 2.3572. Min Act: -0.0000

Data Index: 1044340 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 3.0203. Min Range: -3.0203

Max Act: 2.3611. Min Act: -0.0000

Data Index: 1417211 (Python Code)

Max Activating Token Index: 928

Text #5

Max Range: 3.0203. Min Range: -3.0203

Max Act: 2.4304. Min Act: -0.0000

Data Index: 1446089 (Python Code)

Max Activating Token Index: 443

Text #6

Max Range: 3.0203. Min Range: -3.0203

Max Act: 2.3136. Min Act: -0.0000

Data Index: 1543759 (Python Code)

Max Activating Token Index: 339

Text #7

Max Range: 3.0203. Min Range: -3.0203

Max Act: 2.4292. Min Act: -0.0000

Data Index: 1410085 (Python Code)

Max Activating Token Index: 755

Text #8

Max Range: 3.0203. Min Range: -3.0203

Max Act: 2.2630. Min Act: -0.0000

Data Index: 1104381 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 3.0203. Min Range: -3.0203

Max Act: 2.1420. Min Act: -0.0000

Data Index: 1471424 (Python Code)

Max Activating Token Index: 595

Text #10

Max Range: 3.0203. Min Range: -3.0203

Max Act: 2.2558. Min Act: -0.0000

Data Index: 1134313 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 3.0203. Min Range: -3.0203

Max Act: 2.2000. Min Act: -0.0000

Data Index: 1516358 (Python Code)

Max Activating Token Index: 221

Text #12

Max Range: 3.0203. Min Range: -3.0203

Max Act: 2.1308. Min Act: -0.0000

Data Index: 604431 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 3.0203. Min Range: -3.0203

Max Act: 1.9653. Min Act: -0.0000

Data Index: 1530239 (Python Code)

Max Activating Token Index: 52

Text #14

Max Range: 3.0203. Min Range: -3.0203

Max Act: 2.0640. Min Act: -0.0000

Data Index: 1554883 (Python Code)

Max Activating Token Index: 177

Text #15

Max Range: 3.0203. Min Range: -3.0203

Max Act: 2.0613. Min Act: -0.0000

Data Index: 1492044 (Python Code)

Max Activating Token Index: 56

Text #16

Max Range: 3.0203. Min Range: -3.0203

Max Act: 1.9170. Min Act: -0.0000

Data Index: 808094 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 3.0203. Min Range: -3.0203

Max Act: 1.9337. Min Act: -0.0000

Data Index: 1299359 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 3.0203. Min Range: -3.0203

Max Act: 1.9301. Min Act: -0.0000

Data Index: 978218 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 3.0203. Min Range: -3.0203

Max Act: 2.0332. Min Act: -0.0000

Data Index: 612550 (C4 (Web Text))

Max Activating Token Index: 957