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

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

Neuron 3733 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: 3.9136. Min Range: -3.9136

Max Act: 3.9136. Min Act: -0.0000

Data Index: 1641750 (Python Code)

Max Activating Token Index: 133

Text #1

Max Range: 3.9136. Min Range: -3.9136

Max Act: 3.9065. Min Act: -0.0000

Data Index: 1547984 (Python Code)

Max Activating Token Index: 226

Text #2

Max Range: 3.9136. Min Range: -3.9136

Max Act: 3.8763. Min Act: -0.0000

Data Index: 1391564 (Python Code)

Max Activating Token Index: 1005

Text #3

Max Range: 3.9136. Min Range: -3.9136

Max Act: 3.8000. Min Act: -0.0000

Data Index: 1535483 (Python Code)

Max Activating Token Index: 25

Text #4

Max Range: 3.9136. Min Range: -3.9136

Max Act: 3.6921. Min Act: -0.0000

Data Index: 1547662 (Python Code)

Max Activating Token Index: 190

Text #5

Max Range: 3.9136. Min Range: -3.9136

Max Act: 3.6600. Min Act: -0.0000

Data Index: 1396192 (Python Code)

Max Activating Token Index: 275

Text #6

Max Range: 3.9136. Min Range: -3.9136

Max Act: 3.4385. Min Act: -0.0000

Data Index: 1613180 (Python Code)

Max Activating Token Index: 576

Text #7

Max Range: 3.9136. Min Range: -3.9136

Max Act: 3.4223. Min Act: -0.0000

Data Index: 1445645 (Python Code)

Max Activating Token Index: 763

Text #8

Max Range: 3.9136. Min Range: -3.9136

Max Act: 3.4341. Min Act: -0.0000

Data Index: 1631706 (Python Code)

Max Activating Token Index: 445

Text #9

Max Range: 3.9136. Min Range: -3.9136

Max Act: 3.2824. Min Act: -0.0000

Data Index: 1405693 (Python Code)

Max Activating Token Index: 23

Text #10

Max Range: 3.9136. Min Range: -3.9136

Max Act: 3.4227. Min Act: -0.0000

Data Index: 1389244 (Python Code)

Max Activating Token Index: 45

Text #11

Max Range: 3.9136. Min Range: -3.9136

Max Act: 3.4095. Min Act: -0.0000

Data Index: 1567852 (Python Code)

Max Activating Token Index: 306

Text #12

Max Range: 3.9136. Min Range: -3.9136

Max Act: 3.4098. Min Act: -0.0000

Data Index: 1543043 (Python Code)

Max Activating Token Index: 561

Text #13

Max Range: 3.9136. Min Range: -3.9136

Max Act: 3.2287. Min Act: -0.0000

Data Index: 1583858 (Python Code)

Max Activating Token Index: 709

Text #14

Max Range: 3.9136. Min Range: -3.9136

Max Act: 3.2238. Min Act: -0.0000

Data Index: 1482586 (Python Code)

Max Activating Token Index: 349

Text #15

Max Range: 3.9136. Min Range: -3.9136

Max Act: 3.3939. Min Act: -0.0000

Data Index: 1628094 (Python Code)

Max Activating Token Index: 277

Text #16

Max Range: 3.9136. Min Range: -3.9136

Max Act: 3.2217. Min Act: -0.0000

Data Index: 1587572 (Python Code)

Max Activating Token Index: 129

Text #17

Max Range: 3.9136. Min Range: -3.9136

Max Act: 3.0775. Min Act: -0.0000

Data Index: 1577743 (Python Code)

Max Activating Token Index: 236

Text #18

Max Range: 3.9136. Min Range: -3.9136

Max Act: 3.3231. Min Act: -0.0000

Data Index: 1593307 (Python Code)

Max Activating Token Index: 874

Text #19

Max Range: 3.9136. Min Range: -3.9136

Max Act: 3.3177. Min Act: -0.0000

Data Index: 1553210 (Python Code)

Max Activating Token Index: 140