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

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

Neuron 2964 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7197. Min Range: -3.7197

Max Act: 3.7197. Min Act: -0.0000

Data Index: 1364470 (Python Code)

Max Activating Token Index: 588

Text #1

Max Range: 3.7197. Min Range: -3.7197

Max Act: 3.6296. Min Act: -0.0000

Data Index: 1644066 (Python Code)

Max Activating Token Index: 438

Text #2

Max Range: 3.7197. Min Range: -3.7197

Max Act: 3.2724. Min Act: -0.0000

Data Index: 1395979 (Python Code)

Max Activating Token Index: 606

Text #3

Max Range: 3.7197. Min Range: -3.7197

Max Act: 3.4093. Min Act: -0.0000

Data Index: 1631244 (Python Code)

Max Activating Token Index: 1005

Text #4

Max Range: 3.7197. Min Range: -3.7197

Max Act: 3.5175. Min Act: -0.0000

Data Index: 1542135 (Python Code)

Max Activating Token Index: 519

Text #5

Max Range: 3.7197. Min Range: -3.7197

Max Act: 3.1691. Min Act: -0.0000

Data Index: 1644004 (Python Code)

Max Activating Token Index: 92

Text #6

Max Range: 3.7197. Min Range: -3.7197

Max Act: 3.1124. Min Act: -0.0000

Data Index: 1645578 (Python Code)

Max Activating Token Index: 712

Text #7

Max Range: 3.7197. Min Range: -3.7197

Max Act: 3.4201. Min Act: -0.0000

Data Index: 1499792 (Python Code)

Max Activating Token Index: 613

Text #8

Max Range: 3.7197. Min Range: -3.7197

Max Act: 3.2464. Min Act: -0.0000

Data Index: 1635108 (Python Code)

Max Activating Token Index: 224

Text #9

Max Range: 3.7197. Min Range: -3.7197

Max Act: 3.0889. Min Act: -0.0000

Data Index: 1547551 (Python Code)

Max Activating Token Index: 569

Text #10

Max Range: 3.7197. Min Range: -3.7197

Max Act: 3.0622. Min Act: -0.0000

Data Index: 1128141 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 3.7197. Min Range: -3.7197

Max Act: 3.3587. Min Act: -0.0000

Data Index: 1367510 (Python Code)

Max Activating Token Index: 842

Text #12

Max Range: 3.7197. Min Range: -3.7197

Max Act: 3.0590. Min Act: -0.0000

Data Index: 1574608 (Python Code)

Max Activating Token Index: 951

Text #13

Max Range: 3.7197. Min Range: -3.7197

Max Act: 3.2710. Min Act: -0.0000

Data Index: 967588 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 3.7197. Min Range: -3.7197

Max Act: 3.1679. Min Act: -0.0000

Data Index: 1383576 (Python Code)

Max Activating Token Index: 20

Text #15

Max Range: 3.7197. Min Range: -3.7197

Max Act: 2.4637. Min Act: -0.0000

Data Index: 1639666 (Python Code)

Max Activating Token Index: 779

Text #16

Max Range: 3.7197. Min Range: -3.7197

Max Act: 2.9746. Min Act: -0.0000

Data Index: 1644159 (Python Code)

Max Activating Token Index: 502

Text #17

Max Range: 3.7197. Min Range: -3.7197

Max Act: 3.0520. Min Act: -0.0000

Data Index: 1544775 (Python Code)

Max Activating Token Index: 840

Text #18

Max Range: 3.7197. Min Range: -3.7197

Max Act: 3.0497. Min Act: -0.0000

Data Index: 1477848 (Python Code)

Max Activating Token Index: 52

Text #19

Max Range: 3.7197. Min Range: -3.7197

Max Act: 3.3384. Min Act: -0.0000

Data Index: 1647253 (Python Code)

Max Activating Token Index: 785