Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3014 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1911. Min Act: -0.0001

Data Index: 178508 (C4 (Web Text))

Max Activating Token Index: 522

Text #1

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1916. Min Act: -0.0001

Data Index: 215788 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1801. Min Act: -0.0001

Data Index: 440035 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1604. Min Act: -0.0002

Data Index: 847959 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1564. Min Act: -0.0001

Data Index: 67065 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1432. Min Act: -0.0001

Data Index: 1167051 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1429. Min Act: -0.0001

Data Index: 237941 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1475. Min Act: -0.0001

Data Index: 755609 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1466. Min Act: -0.0001

Data Index: 110603 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1368. Min Act: -0.0002

Data Index: 108401 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1261. Min Act: -0.0001

Data Index: 194135 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1411. Min Act: -0.0001

Data Index: 638992 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1408. Min Act: -0.0001

Data Index: 482872 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1395. Min Act: -0.0001

Data Index: 1318742 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1324. Min Act: -0.0001

Data Index: 843473 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1381. Min Act: -0.0001

Data Index: 1344456 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1377. Min Act: -0.0001

Data Index: 930949 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1463. Min Act: -0.0002

Data Index: 108141 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1368. Min Act: -0.0001

Data Index: 1196275 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1413. Min Act: -0.0001

Data Index: 1635173 (Python Code)

Max Activating Token Index: 78