Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2544 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.6931. Min Act: -0.0001

Data Index: 1401561 (Python Code)

Max Activating Token Index: 16

Text #1

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.6865. Min Act: -0.0001

Data Index: 1567634 (Python Code)

Max Activating Token Index: 583

Text #2

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.4123. Min Act: -0.0001

Data Index: 1435026 (Python Code)

Max Activating Token Index: 748

Text #3

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.6049. Min Act: -0.0001

Data Index: 1569378 (Python Code)

Max Activating Token Index: 235

Text #4

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.4700. Min Act: -0.0001

Data Index: 1561977 (Python Code)

Max Activating Token Index: 722

Text #5

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.5156. Min Act: -0.0001

Data Index: 1535801 (Python Code)

Max Activating Token Index: 875

Text #6

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.2031. Min Act: -0.0001

Data Index: 1467100 (Python Code)

Max Activating Token Index: 316

Text #7

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.2514. Min Act: -0.0001

Data Index: 1434734 (Python Code)

Max Activating Token Index: 86

Text #8

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.2484. Min Act: -0.0001

Data Index: 1448576 (Python Code)

Max Activating Token Index: 275

Text #9

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.2689. Min Act: -0.0001

Data Index: 1488794 (Python Code)

Max Activating Token Index: 291

Text #10

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.2973. Min Act: -0.0001

Data Index: 1519253 (Python Code)

Max Activating Token Index: 144

Text #11

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.2405. Min Act: -0.0001

Data Index: 1480569 (Python Code)

Max Activating Token Index: 609

Text #12

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.2830. Min Act: -0.0001

Data Index: 1519867 (Python Code)

Max Activating Token Index: 337

Text #13

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.1971. Min Act: -0.0001

Data Index: 1580319 (Python Code)

Max Activating Token Index: 472

Text #14

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.1212. Min Act: -0.0001

Data Index: 1443804 (Python Code)

Max Activating Token Index: 302

Text #15

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.1016. Min Act: -0.0001

Data Index: 1607467 (Python Code)

Max Activating Token Index: 653

Text #16

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.1776. Min Act: -0.0001

Data Index: 1577785 (Python Code)

Max Activating Token Index: 169

Text #17

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.2031. Min Act: -0.0001

Data Index: 1552671 (Python Code)

Max Activating Token Index: 772

Text #18

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.2027. Min Act: -0.0001

Data Index: 1569957 (Python Code)

Max Activating Token Index: 144

Text #19

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.1857. Min Act: -0.0001

Data Index: 1407979 (Python Code)

Max Activating Token Index: 625