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

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

Neuron 1329 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: 0.7758. Min Range: -0.7758

Max Act: 0.7758. Min Act: -0.0000

Data Index: 1549044 (Python Code)

Max Activating Token Index: 927

Text #1

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.7427. Min Act: -0.0000

Data Index: 1642100 (Python Code)

Max Activating Token Index: 497

Text #2

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6732. Min Act: -0.0000

Data Index: 1570523 (Python Code)

Max Activating Token Index: 62

Text #3

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6717. Min Act: -0.0000

Data Index: 1633031 (Python Code)

Max Activating Token Index: 398

Text #4

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6483. Min Act: -0.0000

Data Index: 1502990 (Python Code)

Max Activating Token Index: 146

Text #5

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6476. Min Act: -0.0000

Data Index: 1501184 (Python Code)

Max Activating Token Index: 496

Text #6

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6516. Min Act: -0.0000

Data Index: 1520828 (Python Code)

Max Activating Token Index: 225

Text #7

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1633968 (Python Code)

Max Activating Token Index: 199

Text #8

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6278. Min Act: -0.0000

Data Index: 1443577 (Python Code)

Max Activating Token Index: 23

Text #9

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.5993. Min Act: -0.0000

Data Index: 1652465 (Python Code)

Max Activating Token Index: 634

Text #10

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.5348. Min Act: -0.0000

Data Index: 1400641 (Python Code)

Max Activating Token Index: 1018

Text #11

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.5299. Min Act: -0.0000

Data Index: 1505199 (Python Code)

Max Activating Token Index: 935

Text #12

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.5586. Min Act: -0.0000

Data Index: 1547403 (Python Code)

Max Activating Token Index: 43

Text #13

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.5270. Min Act: -0.0001

Data Index: 1570709 (Python Code)

Max Activating Token Index: 190

Text #14

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1426102 (Python Code)

Max Activating Token Index: 610

Text #15

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.5319. Min Act: -0.0000

Data Index: 1546201 (Python Code)

Max Activating Token Index: 459

Text #16

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.5136. Min Act: -0.0000

Data Index: 1372124 (Python Code)

Max Activating Token Index: 11

Text #17

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.5443. Min Act: -0.0000

Data Index: 1384484 (Python Code)

Max Activating Token Index: 500

Text #18

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.5030. Min Act: -0.0000

Data Index: 1375387 (Python Code)

Max Activating Token Index: 795

Text #19

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.4970. Min Act: -0.0000

Data Index: 1583766 (Python Code)

Max Activating Token Index: 556