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

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

Neuron 2089 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.6225. Min Act: -0.0000

Data Index: 1491233 (Python Code)

Max Activating Token Index: 46

Text #1

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.6176. Min Act: -0.0000

Data Index: 1626363 (Python Code)

Max Activating Token Index: 40

Text #2

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.6114. Min Act: -0.0000

Data Index: 1502287 (Python Code)

Max Activating Token Index: 12

Text #3

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5892. Min Act: -0.0000

Data Index: 1407601 (Python Code)

Max Activating Token Index: 48

Text #4

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5615. Min Act: -0.0000

Data Index: 1528500 (Python Code)

Max Activating Token Index: 108

Text #5

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5598. Min Act: -0.0000

Data Index: 1497173 (Python Code)

Max Activating Token Index: 49

Text #6

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5738. Min Act: -0.0000

Data Index: 1400050 (Python Code)

Max Activating Token Index: 18

Text #7

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5351. Min Act: -0.0000

Data Index: 1505527 (Python Code)

Max Activating Token Index: 109

Text #8

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5822. Min Act: -0.0000

Data Index: 1459616 (Python Code)

Max Activating Token Index: 13

Text #9

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5561. Min Act: -0.0000

Data Index: 1498436 (Python Code)

Max Activating Token Index: 11

Text #10

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5289. Min Act: -0.0000

Data Index: 1568726 (Python Code)

Max Activating Token Index: 49

Text #11

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5271. Min Act: -0.0000

Data Index: 1514987 (Python Code)

Max Activating Token Index: 43

Text #12

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5367. Min Act: -0.0000

Data Index: 1506280 (Python Code)

Max Activating Token Index: 41

Text #13

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5298. Min Act: -0.0000

Data Index: 1611431 (Python Code)

Max Activating Token Index: 13

Text #14

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5467. Min Act: -0.0000

Data Index: 1551488 (Python Code)

Max Activating Token Index: 44

Text #15

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5446. Min Act: -0.0000

Data Index: 1560735 (Python Code)

Max Activating Token Index: 13

Text #16

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5582. Min Act: -0.0000

Data Index: 1493343 (Python Code)

Max Activating Token Index: 114

Text #17

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5007. Min Act: -0.0000

Data Index: 1376044 (Python Code)

Max Activating Token Index: 104

Text #18

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5130. Min Act: -0.0000

Data Index: 1423449 (Python Code)

Max Activating Token Index: 13

Text #19

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.4967. Min Act: -0.0000

Data Index: 1648279 (Python Code)

Max Activating Token Index: 114