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

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

Neuron 1188 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: 5.3226. Min Range: -5.3226

Max Act: 5.3226. Min Act: -0.0000

Data Index: 1465289 (Python Code)

Max Activating Token Index: 900

Text #1

Max Range: 5.3226. Min Range: -5.3226

Max Act: 4.7578. Min Act: -0.0000

Data Index: 1610802 (Python Code)

Max Activating Token Index: 959

Text #2

Max Range: 5.3226. Min Range: -5.3226

Max Act: 4.8785. Min Act: -0.0000

Data Index: 1405720 (Python Code)

Max Activating Token Index: 903

Text #3

Max Range: 5.3226. Min Range: -5.3226

Max Act: 4.6937. Min Act: -0.0000

Data Index: 1386796 (Python Code)

Max Activating Token Index: 915

Text #4

Max Range: 5.3226. Min Range: -5.3226

Max Act: 3.9482. Min Act: -0.0000

Data Index: 1474593 (Python Code)

Max Activating Token Index: 754

Text #5

Max Range: 5.3226. Min Range: -5.3226

Max Act: 4.5769. Min Act: -0.0000

Data Index: 1462568 (Python Code)

Max Activating Token Index: 316

Text #6

Max Range: 5.3226. Min Range: -5.3226

Max Act: 4.2314. Min Act: -0.0000

Data Index: 1623288 (Python Code)

Max Activating Token Index: 26

Text #7

Max Range: 5.3226. Min Range: -5.3226

Max Act: 4.2661. Min Act: -0.0000

Data Index: 1375214 (Python Code)

Max Activating Token Index: 29

Text #8

Max Range: 5.3226. Min Range: -5.3226

Max Act: 4.3644. Min Act: -0.0000

Data Index: 1362062 (Python Code)

Max Activating Token Index: 55

Text #9

Max Range: 5.3226. Min Range: -5.3226

Max Act: 3.8049. Min Act: -0.0000

Data Index: 1414971 (Python Code)

Max Activating Token Index: 268

Text #10

Max Range: 5.3226. Min Range: -5.3226

Max Act: 4.5911. Min Act: -0.0000

Data Index: 1563157 (Python Code)

Max Activating Token Index: 68

Text #11

Max Range: 5.3226. Min Range: -5.3226

Max Act: 3.9375. Min Act: -0.0000

Data Index: 1445639 (Python Code)

Max Activating Token Index: 83

Text #12

Max Range: 5.3226. Min Range: -5.3226

Max Act: 4.2389. Min Act: -0.0000

Data Index: 1600585 (Python Code)

Max Activating Token Index: 433

Text #13

Max Range: 5.3226. Min Range: -5.3226

Max Act: 4.2279. Min Act: -0.0000

Data Index: 1486983 (Python Code)

Max Activating Token Index: 304

Text #14

Max Range: 5.3226. Min Range: -5.3226

Max Act: 4.3701. Min Act: -0.0000

Data Index: 1376124 (Python Code)

Max Activating Token Index: 61

Text #15

Max Range: 5.3226. Min Range: -5.3226

Max Act: 4.3701. Min Act: -0.0000

Data Index: 1593151 (Python Code)

Max Activating Token Index: 61

Text #16

Max Range: 5.3226. Min Range: -5.3226

Max Act: 3.8854. Min Act: -0.0000

Data Index: 1595238 (Python Code)

Max Activating Token Index: 574

Text #17

Max Range: 5.3226. Min Range: -5.3226

Max Act: 3.9520. Min Act: -0.0000

Data Index: 1409677 (Python Code)

Max Activating Token Index: 694

Text #18

Max Range: 5.3226. Min Range: -5.3226

Max Act: 4.0859. Min Act: -0.0000

Data Index: 1379330 (Python Code)

Max Activating Token Index: 592

Text #19

Max Range: 5.3226. Min Range: -5.3226

Max Act: 4.0974. Min Act: -0.0000

Data Index: 1419256 (Python Code)

Max Activating Token Index: 408