Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2138 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6717. Min Range: -1.6717

Max Act: 1.5906. Min Act: -0.0000

Data Index: 222860 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 1.6717. Min Range: -1.6717

Max Act: 1.6717. Min Act: -0.0000

Data Index: 1426074 (Python Code)

Max Activating Token Index: 384

Text #2

Max Range: 1.6717. Min Range: -1.6717

Max Act: 1.4675. Min Act: -0.0000

Data Index: 1562067 (Python Code)

Max Activating Token Index: 1020

Text #3

Max Range: 1.6717. Min Range: -1.6717

Max Act: 1.5445. Min Act: -0.0000

Data Index: 1644125 (Python Code)

Max Activating Token Index: 691

Text #4

Max Range: 1.6717. Min Range: -1.6717

Max Act: 1.5662. Min Act: -0.0000

Data Index: 1611841 (Python Code)

Max Activating Token Index: 744

Text #5

Max Range: 1.6717. Min Range: -1.6717

Max Act: 1.3546. Min Act: -0.0000

Data Index: 1521626 (Python Code)

Max Activating Token Index: 673

Text #6

Max Range: 1.6717. Min Range: -1.6717

Max Act: 1.5202. Min Act: -0.0000

Data Index: 1576619 (Python Code)

Max Activating Token Index: 786

Text #7

Max Range: 1.6717. Min Range: -1.6717

Max Act: 1.3443. Min Act: -0.0000

Data Index: 1447945 (Python Code)

Max Activating Token Index: 923

Text #8

Max Range: 1.6717. Min Range: -1.6717

Max Act: 1.4439. Min Act: -0.0000

Data Index: 1589712 (Python Code)

Max Activating Token Index: 491

Text #9

Max Range: 1.6717. Min Range: -1.6717

Max Act: 1.5177. Min Act: -0.0000

Data Index: 1590908 (Python Code)

Max Activating Token Index: 518

Text #10

Max Range: 1.6717. Min Range: -1.6717

Max Act: 1.5074. Min Act: -0.0000

Data Index: 1377482 (Python Code)

Max Activating Token Index: 126

Text #11

Max Range: 1.6717. Min Range: -1.6717

Max Act: 1.4561. Min Act: -0.0000

Data Index: 919072 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 1.6717. Min Range: -1.6717

Max Act: 1.4463. Min Act: -0.0000

Data Index: 207185 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 1.6717. Min Range: -1.6717

Max Act: 1.4596. Min Act: -0.0000

Data Index: 503843 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 1.6717. Min Range: -1.6717

Max Act: 1.4317. Min Act: -0.0000

Data Index: 1132068 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 1.6717. Min Range: -1.6717

Max Act: 1.4392. Min Act: -0.0000

Data Index: 1612507 (Python Code)

Max Activating Token Index: 915

Text #16

Max Range: 1.6717. Min Range: -1.6717

Max Act: 1.1556. Min Act: -0.0000

Data Index: 1436551 (Python Code)

Max Activating Token Index: 339

Text #17

Max Range: 1.6717. Min Range: -1.6717

Max Act: 1.3434. Min Act: -0.0000

Data Index: 1529563 (Python Code)

Max Activating Token Index: 514

Text #18

Max Range: 1.6717. Min Range: -1.6717

Max Act: 1.3461. Min Act: -0.0000

Data Index: 1418930 (Python Code)

Max Activating Token Index: 979

Text #19

Max Range: 1.6717. Min Range: -1.6717

Max Act: 1.2867. Min Act: -0.0000

Data Index: 1515957 (Python Code)

Max Activating Token Index: 604