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

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

Neuron 3049 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6920. Min Range: -5.6920

Max Act: 5.6920. Min Act: -0.0000

Data Index: 1525987 (Python Code)

Max Activating Token Index: 412

Text #1

Max Range: 5.6920. Min Range: -5.6920

Max Act: 4.7466. Min Act: -0.0000

Data Index: 1442923 (Python Code)

Max Activating Token Index: 227

Text #2

Max Range: 5.6920. Min Range: -5.6920

Max Act: 4.6138. Min Act: -0.0000

Data Index: 1613806 (Python Code)

Max Activating Token Index: 107

Text #3

Max Range: 5.6920. Min Range: -5.6920

Max Act: 4.8005. Min Act: -0.0000

Data Index: 1596036 (Python Code)

Max Activating Token Index: 325

Text #4

Max Range: 5.6920. Min Range: -5.6920

Max Act: 4.6395. Min Act: -0.0000

Data Index: 1541057 (Python Code)

Max Activating Token Index: 60

Text #5

Max Range: 5.6920. Min Range: -5.6920

Max Act: 4.6230. Min Act: -0.0000

Data Index: 1384598 (Python Code)

Max Activating Token Index: 807

Text #6

Max Range: 5.6920. Min Range: -5.6920

Max Act: 4.5368. Min Act: -0.0000

Data Index: 1643678 (Python Code)

Max Activating Token Index: 14

Text #7

Max Range: 5.6920. Min Range: -5.6920

Max Act: 4.5344. Min Act: -0.0000

Data Index: 1397652 (Python Code)

Max Activating Token Index: 12

Text #8

Max Range: 5.6920. Min Range: -5.6920

Max Act: 4.5066. Min Act: -0.0000

Data Index: 1529941 (Python Code)

Max Activating Token Index: 22

Text #9

Max Range: 5.6920. Min Range: -5.6920

Max Act: 4.4937. Min Act: -0.0000

Data Index: 1398241 (Python Code)

Max Activating Token Index: 51

Text #10

Max Range: 5.6920. Min Range: -5.6920

Max Act: 4.3727. Min Act: -0.0000

Data Index: 1564122 (Python Code)

Max Activating Token Index: 110

Text #11

Max Range: 5.6920. Min Range: -5.6920

Max Act: 4.3664. Min Act: -0.0000

Data Index: 1610643 (Python Code)

Max Activating Token Index: 12

Text #12

Max Range: 5.6920. Min Range: -5.6920

Max Act: 4.3550. Min Act: -0.0000

Data Index: 1478465 (Python Code)

Max Activating Token Index: 62

Text #13

Max Range: 5.6920. Min Range: -5.6920

Max Act: 4.1142. Min Act: -0.0000

Data Index: 1428761 (Python Code)

Max Activating Token Index: 12

Text #14

Max Range: 5.6920. Min Range: -5.6920

Max Act: 4.2599. Min Act: -0.0000

Data Index: 1647689 (Python Code)

Max Activating Token Index: 54

Text #15

Max Range: 5.6920. Min Range: -5.6920

Max Act: 3.8301. Min Act: -0.0000

Data Index: 1384504 (Python Code)

Max Activating Token Index: 267

Text #16

Max Range: 5.6920. Min Range: -5.6920

Max Act: 4.1557. Min Act: -0.0000

Data Index: 1445437 (Python Code)

Max Activating Token Index: 109

Text #17

Max Range: 5.6920. Min Range: -5.6920

Max Act: 4.1486. Min Act: -0.0000

Data Index: 1515839 (Python Code)

Max Activating Token Index: 5

Text #18

Max Range: 5.6920. Min Range: -5.6920

Max Act: 4.1410. Min Act: -0.0000

Data Index: 1610291 (Python Code)

Max Activating Token Index: 14

Text #19

Max Range: 5.6920. Min Range: -5.6920

Max Act: 3.9976. Min Act: -0.0000

Data Index: 1536228 (Python Code)

Max Activating Token Index: 39