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

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

Neuron 5372 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.2161. Min Act: -0.0001

Data Index: 1336749 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1900. Min Act: -0.0001

Data Index: 476184 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1842. Min Act: -0.0001

Data Index: 217891 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1627. Min Act: -0.0001

Data Index: 917289 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1686. Min Act: -0.0001

Data Index: 1116681 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1842. Min Act: -0.0001

Data Index: 1284074 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1759. Min Act: -0.0001

Data Index: 776521 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1686. Min Act: -0.0001

Data Index: 580897 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1366. Min Act: -0.0001

Data Index: 1663 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1577. Min Act: -0.0001

Data Index: 19750 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1596. Min Act: -0.0001

Data Index: 1169698 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1588. Min Act: -0.0001

Data Index: 737846 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1497. Min Act: -0.0001

Data Index: 871057 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1512. Min Act: -0.0001

Data Index: 139788 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1554. Min Act: -0.0001

Data Index: 1117641 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1444. Min Act: -0.0001

Data Index: 645400 (C4 (Web Text))

Max Activating Token Index: 7

Text #16

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1559. Min Act: -0.0001

Data Index: 908039 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1545. Min Act: -0.0001

Data Index: 953467 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1590. Min Act: -0.0001

Data Index: 1153336 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1462. Min Act: -0.0001

Data Index: 821886 (C4 (Web Text))

Max Activating Token Index: 591