Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5588 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1238. Min Range: -2.1238

Max Act: 2.1238. Min Act: -0.0000

Data Index: 1468030 (Python Code)

Max Activating Token Index: 641

Text #1

Max Range: 2.1238. Min Range: -2.1238

Max Act: 1.9342. Min Act: -0.0000

Data Index: 1602355 (Python Code)

Max Activating Token Index: 771

Text #2

Max Range: 2.1238. Min Range: -2.1238

Max Act: 1.8727. Min Act: -0.0000

Data Index: 1407765 (Python Code)

Max Activating Token Index: 735

Text #3

Max Range: 2.1238. Min Range: -2.1238

Max Act: 1.7456. Min Act: -0.0000

Data Index: 1527043 (Python Code)

Max Activating Token Index: 876

Text #4

Max Range: 2.1238. Min Range: -2.1238

Max Act: 1.6363. Min Act: -0.0000

Data Index: 1515494 (Python Code)

Max Activating Token Index: 785

Text #5

Max Range: 2.1238. Min Range: -2.1238

Max Act: 1.6497. Min Act: -0.0000

Data Index: 1435750 (Python Code)

Max Activating Token Index: 823

Text #6

Max Range: 2.1238. Min Range: -2.1238

Max Act: 1.6703. Min Act: -0.0000

Data Index: 1444972 (Python Code)

Max Activating Token Index: 870

Text #7

Max Range: 2.1238. Min Range: -2.1238

Max Act: 1.6597. Min Act: -0.0000

Data Index: 1617134 (Python Code)

Max Activating Token Index: 883

Text #8

Max Range: 2.1238. Min Range: -2.1238

Max Act: 1.5478. Min Act: -0.0000

Data Index: 1472937 (Python Code)

Max Activating Token Index: 218

Text #9

Max Range: 2.1238. Min Range: -2.1238

Max Act: 1.5290. Min Act: -0.0000

Data Index: 1508438 (Python Code)

Max Activating Token Index: 580

Text #10

Max Range: 2.1238. Min Range: -2.1238

Max Act: 1.5255. Min Act: -0.0000

Data Index: 1425540 (Python Code)

Max Activating Token Index: 197

Text #11

Max Range: 2.1238. Min Range: -2.1238

Max Act: 1.4259. Min Act: -0.0000

Data Index: 1543237 (Python Code)

Max Activating Token Index: 754

Text #12

Max Range: 2.1238. Min Range: -2.1238

Max Act: 1.5031. Min Act: -0.0000

Data Index: 1583034 (Python Code)

Max Activating Token Index: 947

Text #13

Max Range: 2.1238. Min Range: -2.1238

Max Act: 1.5019. Min Act: -0.0000

Data Index: 1572139 (Python Code)

Max Activating Token Index: 495

Text #14

Max Range: 2.1238. Min Range: -2.1238

Max Act: 1.5067. Min Act: -0.0000

Data Index: 1635801 (Python Code)

Max Activating Token Index: 651

Text #15

Max Range: 2.1238. Min Range: -2.1238

Max Act: 1.5275. Min Act: -0.0000

Data Index: 1425089 (Python Code)

Max Activating Token Index: 309

Text #16

Max Range: 2.1238. Min Range: -2.1238

Max Act: 1.4813. Min Act: -0.0000

Data Index: 1609904 (Python Code)

Max Activating Token Index: 246

Text #17

Max Range: 2.1238. Min Range: -2.1238

Max Act: 1.5691. Min Act: -0.0000

Data Index: 1403433 (Python Code)

Max Activating Token Index: 266

Text #18

Max Range: 2.1238. Min Range: -2.1238

Max Act: 1.4446. Min Act: -0.0000

Data Index: 1471444 (Python Code)

Max Activating Token Index: 688

Text #19

Max Range: 2.1238. Min Range: -2.1238

Max Act: 1.4416. Min Act: -0.0000

Data Index: 1488854 (Python Code)

Max Activating Token Index: 552