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

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

Neuron 630 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3760. Min Act: -0.0001

Data Index: 256063 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3312. Min Act: -0.0001

Data Index: 1555051 (Python Code)

Max Activating Token Index: 368

Text #2

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3217. Min Act: -0.0001

Data Index: 1380497 (Python Code)

Max Activating Token Index: 316

Text #3

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3257. Min Act: -0.0001

Data Index: 1157689 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2936. Min Act: -0.0001

Data Index: 1368326 (Python Code)

Max Activating Token Index: 129

Text #5

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2872. Min Act: -0.0001

Data Index: 1539384 (Python Code)

Max Activating Token Index: 223

Text #6

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2774. Min Act: -0.0001

Data Index: 123082 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2865. Min Act: -0.0000

Data Index: 1425504 (Python Code)

Max Activating Token Index: 45

Text #8

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2843. Min Act: -0.0001

Data Index: 1616887 (Python Code)

Max Activating Token Index: 571

Text #9

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2729. Min Act: -0.0001

Data Index: 1572704 (Python Code)

Max Activating Token Index: 965

Text #10

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2765. Min Act: -0.0001

Data Index: 1554282 (Python Code)

Max Activating Token Index: 771

Text #11

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2928. Min Act: -0.0001

Data Index: 1624457 (Python Code)

Max Activating Token Index: 836

Text #12

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2898. Min Act: -0.0001

Data Index: 1355342 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2399. Min Act: -0.0001

Data Index: 1291613 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2687. Min Act: -0.0001

Data Index: 1184341 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2621. Min Act: -0.0001

Data Index: 1629793 (Python Code)

Max Activating Token Index: 992

Text #16

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2684. Min Act: -0.0001

Data Index: 1572254 (Python Code)

Max Activating Token Index: 145

Text #17

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2779. Min Act: -0.0001

Data Index: 1278585 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2707. Min Act: -0.0001

Data Index: 1630077 (Python Code)

Max Activating Token Index: 639

Text #19

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2263. Min Act: -0.0001

Data Index: 1404260 (Python Code)

Max Activating Token Index: 996