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

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

Neuron 4631 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8846. Min Range: -4.8846

Max Act: 4.8846. Min Act: -0.0000

Data Index: 1016704 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 4.8846. Min Range: -4.8846

Max Act: 4.2210. Min Act: -0.0000

Data Index: 1202731 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 4.8846. Min Range: -4.8846

Max Act: 3.8834. Min Act: -0.0000

Data Index: 1300141 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 4.8846. Min Range: -4.8846

Max Act: 3.0073. Min Act: -0.0000

Data Index: 1509228 (Python Code)

Max Activating Token Index: 302

Text #4

Max Range: 4.8846. Min Range: -4.8846

Max Act: 3.1316. Min Act: -0.0000

Data Index: 1635241 (Python Code)

Max Activating Token Index: 563

Text #5

Max Range: 4.8846. Min Range: -4.8846

Max Act: 3.1113. Min Act: -0.0000

Data Index: 1417578 (Python Code)

Max Activating Token Index: 183

Text #6

Max Range: 4.8846. Min Range: -4.8846

Max Act: 3.0463. Min Act: -0.0000

Data Index: 826701 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 4.8846. Min Range: -4.8846

Max Act: 2.9970. Min Act: -0.0000

Data Index: 1364027 (Python Code)

Max Activating Token Index: 573

Text #8

Max Range: 4.8846. Min Range: -4.8846

Max Act: 3.0025. Min Act: -0.0000

Data Index: 1578470 (Python Code)

Max Activating Token Index: 719

Text #9

Max Range: 4.8846. Min Range: -4.8846

Max Act: 2.7683. Min Act: -0.0000

Data Index: 599245 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 4.8846. Min Range: -4.8846

Max Act: 2.9297. Min Act: -0.0000

Data Index: 437578 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 4.8846. Min Range: -4.8846

Max Act: 3.0164. Min Act: -0.0000

Data Index: 1629302 (Python Code)

Max Activating Token Index: 141

Text #12

Max Range: 4.8846. Min Range: -4.8846

Max Act: 2.7446. Min Act: -0.0000

Data Index: 1589175 (Python Code)

Max Activating Token Index: 291

Text #13

Max Range: 4.8846. Min Range: -4.8846

Max Act: 2.7130. Min Act: -0.0000

Data Index: 1615591 (Python Code)

Max Activating Token Index: 1011

Text #14

Max Range: 4.8846. Min Range: -4.8846

Max Act: 2.9405. Min Act: -0.0000

Data Index: 298283 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 4.8846. Min Range: -4.8846

Max Act: 2.7313. Min Act: -0.0000

Data Index: 1592467 (Python Code)

Max Activating Token Index: 498

Text #16

Max Range: 4.8846. Min Range: -4.8846

Max Act: 2.7335. Min Act: -0.0000

Data Index: 1645472 (Python Code)

Max Activating Token Index: 766

Text #17

Max Range: 4.8846. Min Range: -4.8846

Max Act: 2.5113. Min Act: -0.0000

Data Index: 1310593 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 4.8846. Min Range: -4.8846

Max Act: 2.7523. Min Act: -0.0000

Data Index: 781923 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 4.8846. Min Range: -4.8846

Max Act: 2.6007. Min Act: -0.0000

Data Index: 1534401 (Python Code)

Max Activating Token Index: 1021