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

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

Neuron 3454 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.9834. Min Act: -0.0000

Data Index: 1613496 (Python Code)

Max Activating Token Index: 646

Text #1

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.9812. Min Act: -0.0000

Data Index: 1647489 (Python Code)

Max Activating Token Index: 579

Text #2

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.8461. Min Act: -0.0000

Data Index: 1484211 (Python Code)

Max Activating Token Index: 83

Text #3

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.6407. Min Act: -0.0000

Data Index: 1599811 (Python Code)

Max Activating Token Index: 64

Text #4

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.7265. Min Act: -0.0000

Data Index: 1480404 (Python Code)

Max Activating Token Index: 836

Text #5

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.7581. Min Act: -0.0000

Data Index: 1592890 (Python Code)

Max Activating Token Index: 740

Text #6

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.6272. Min Act: -0.0000

Data Index: 1554281 (Python Code)

Max Activating Token Index: 151

Text #7

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.5511. Min Act: -0.0000

Data Index: 1550272 (Python Code)

Max Activating Token Index: 260

Text #8

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.0703. Min Act: -0.0000

Data Index: 1555284 (Python Code)

Max Activating Token Index: 314

Text #9

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.4146. Min Act: -0.0000

Data Index: 1628076 (Python Code)

Max Activating Token Index: 126

Text #10

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.4956. Min Act: -0.0000

Data Index: 1596494 (Python Code)

Max Activating Token Index: 826

Text #11

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.3695. Min Act: -0.0000

Data Index: 1562306 (Python Code)

Max Activating Token Index: 812

Text #12

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.4128. Min Act: -0.0000

Data Index: 1434919 (Python Code)

Max Activating Token Index: 80

Text #13

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.4603. Min Act: -0.0000

Data Index: 1393949 (Python Code)

Max Activating Token Index: 957

Text #14

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.4182. Min Act: -0.0000

Data Index: 1608727 (Python Code)

Max Activating Token Index: 957

Text #15

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.4144. Min Act: 0.0000

Data Index: 1490956 (Python Code)

Max Activating Token Index: 81

Text #16

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.4373. Min Act: -0.0000

Data Index: 1557165 (Python Code)

Max Activating Token Index: 452

Text #17

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.4358. Min Act: -0.0000

Data Index: 1425911 (Python Code)

Max Activating Token Index: 40

Text #18

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.3059. Min Act: -0.0000

Data Index: 1566943 (Python Code)

Max Activating Token Index: 262

Text #19

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.2766. Min Act: -0.0000

Data Index: 1503346 (Python Code)

Max Activating Token Index: 644