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

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

Neuron 221 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.7342. Min Act: -0.0000

Data Index: 1611479 (Python Code)

Max Activating Token Index: 864

Text #1

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.7005. Min Act: -0.0000

Data Index: 884601 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.6647. Min Act: -0.0000

Data Index: 1391652 (Python Code)

Max Activating Token Index: 170

Text #3

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.6872. Min Act: -0.0000

Data Index: 189769 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.6525. Min Act: -0.0000

Data Index: 1643215 (Python Code)

Max Activating Token Index: 153

Text #5

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.6155. Min Act: 0.0000

Data Index: 1467329 (Python Code)

Max Activating Token Index: 60

Text #6

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.6148. Min Act: -0.0000

Data Index: 1431471 (Python Code)

Max Activating Token Index: 812

Text #7

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.5927. Min Act: -0.0000

Data Index: 1378354 (Python Code)

Max Activating Token Index: 1016

Text #8

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.6296. Min Act: 0.0000

Data Index: 1514852 (Python Code)

Max Activating Token Index: 966

Text #9

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.6001. Min Act: -0.0000

Data Index: 1595368 (Python Code)

Max Activating Token Index: 559

Text #10

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.6024. Min Act: -0.0000

Data Index: 1483502 (Python Code)

Max Activating Token Index: 541

Text #11

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.5750. Min Act: -0.0000

Data Index: 1379231 (Python Code)

Max Activating Token Index: 683

Text #12

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.5941. Min Act: -0.0000

Data Index: 823041 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.5750. Min Act: -0.0000

Data Index: 1369831 (Python Code)

Max Activating Token Index: 94

Text #14

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.5512. Min Act: -0.0000

Data Index: 1559416 (Python Code)

Max Activating Token Index: 129

Text #15

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.5707. Min Act: -0.0000

Data Index: 480823 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.5479. Min Act: -0.0000

Data Index: 1623766 (Python Code)

Max Activating Token Index: 302

Text #17

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.5551. Min Act: -0.0000

Data Index: 1597031 (Python Code)

Max Activating Token Index: 504

Text #18

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.5402. Min Act: -0.0000

Data Index: 359199 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.5222. Min Act: -0.0000

Data Index: 1032897 (C4 (Web Text))

Max Activating Token Index: 824