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

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

Neuron 6098 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.5782. Min Act: -0.0002

Data Index: 1439139 (Python Code)

Max Activating Token Index: 819

Text #1

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.5524. Min Act: -0.0002

Data Index: 1505850 (Python Code)

Max Activating Token Index: 147

Text #2

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.5512. Min Act: -0.0002

Data Index: 1433662 (Python Code)

Max Activating Token Index: 618

Text #3

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.5225. Min Act: -0.0002

Data Index: 1389287 (Python Code)

Max Activating Token Index: 169

Text #4

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4779. Min Act: -0.0002

Data Index: 1422567 (Python Code)

Max Activating Token Index: 521

Text #5

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4887. Min Act: -0.0002

Data Index: 1641948 (Python Code)

Max Activating Token Index: 528

Text #6

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4739. Min Act: -0.0002

Data Index: 1577300 (Python Code)

Max Activating Token Index: 606

Text #7

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.3954. Min Act: -0.0002

Data Index: 1378871 (Python Code)

Max Activating Token Index: 778

Text #8

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4387. Min Act: -0.0002

Data Index: 1577873 (Python Code)

Max Activating Token Index: 475

Text #9

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4369. Min Act: -0.0002

Data Index: 1389351 (Python Code)

Max Activating Token Index: 154

Text #10

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4375. Min Act: -0.0002

Data Index: 1439275 (Python Code)

Max Activating Token Index: 213

Text #11

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4385. Min Act: -0.0002

Data Index: 1516854 (Python Code)

Max Activating Token Index: 316

Text #12

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4216. Min Act: -0.0002

Data Index: 1618632 (Python Code)

Max Activating Token Index: 62

Text #13

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4351. Min Act: -0.0002

Data Index: 1477909 (Python Code)

Max Activating Token Index: 330

Text #14

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4145. Min Act: -0.0002

Data Index: 1438582 (Python Code)

Max Activating Token Index: 126

Text #15

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4220. Min Act: -0.0002

Data Index: 1645832 (Python Code)

Max Activating Token Index: 838

Text #16

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4215. Min Act: -0.0002

Data Index: 1366844 (Python Code)

Max Activating Token Index: 190

Text #17

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.3917. Min Act: -0.0002

Data Index: 1455439 (Python Code)

Max Activating Token Index: 191

Text #18

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4026. Min Act: -0.0002

Data Index: 1415262 (Python Code)

Max Activating Token Index: 758

Text #19

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4024. Min Act: -0.0002

Data Index: 1542198 (Python Code)

Max Activating Token Index: 889