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

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

Neuron 4405 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.8615. Min Range: -2.8615

Max Act: 2.8615. Min Act: -0.0000

Data Index: 1448700 (Python Code)

Max Activating Token Index: 962

Text #1

Max Range: 2.8615. Min Range: -2.8615

Max Act: 2.5013. Min Act: -0.0000

Data Index: 1531031 (Python Code)

Max Activating Token Index: 774

Text #2

Max Range: 2.8615. Min Range: -2.8615

Max Act: 2.3277. Min Act: -0.0000

Data Index: 1513340 (Python Code)

Max Activating Token Index: 27

Text #3

Max Range: 2.8615. Min Range: -2.8615

Max Act: 2.5192. Min Act: -0.0000

Data Index: 1538457 (Python Code)

Max Activating Token Index: 970

Text #4

Max Range: 2.8615. Min Range: -2.8615

Max Act: 2.2391. Min Act: -0.0000

Data Index: 1428577 (Python Code)

Max Activating Token Index: 975

Text #5

Max Range: 2.8615. Min Range: -2.8615

Max Act: 2.2363. Min Act: -0.0000

Data Index: 1421718 (Python Code)

Max Activating Token Index: 251

Text #6

Max Range: 2.8615. Min Range: -2.8615

Max Act: 2.1247. Min Act: -0.0000

Data Index: 1422191 (Python Code)

Max Activating Token Index: 773

Text #7

Max Range: 2.8615. Min Range: -2.8615

Max Act: 2.1286. Min Act: -0.0000

Data Index: 1619900 (Python Code)

Max Activating Token Index: 211

Text #8

Max Range: 2.8615. Min Range: -2.8615

Max Act: 2.1334. Min Act: -0.0000

Data Index: 1615649 (Python Code)

Max Activating Token Index: 786

Text #9

Max Range: 2.8615. Min Range: -2.8615

Max Act: 2.1421. Min Act: -0.0000

Data Index: 1368953 (Python Code)

Max Activating Token Index: 784

Text #10

Max Range: 2.8615. Min Range: -2.8615

Max Act: 2.1373. Min Act: -0.0000

Data Index: 1379757 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 2.8615. Min Range: -2.8615

Max Act: 2.0979. Min Act: -0.0000

Data Index: 1531094 (Python Code)

Max Activating Token Index: 368

Text #12

Max Range: 2.8615. Min Range: -2.8615

Max Act: 2.0288. Min Act: -0.0000

Data Index: 1418804 (Python Code)

Max Activating Token Index: 836

Text #13

Max Range: 2.8615. Min Range: -2.8615

Max Act: 2.0190. Min Act: -0.0000

Data Index: 1482219 (Python Code)

Max Activating Token Index: 1010

Text #14

Max Range: 2.8615. Min Range: -2.8615

Max Act: 2.0073. Min Act: -0.0000

Data Index: 1441899 (Python Code)

Max Activating Token Index: 291

Text #15

Max Range: 2.8615. Min Range: -2.8615

Max Act: 2.0017. Min Act: -0.0000

Data Index: 1394530 (Python Code)

Max Activating Token Index: 452

Text #16

Max Range: 2.8615. Min Range: -2.8615

Max Act: 1.8498. Min Act: -0.0000

Data Index: 1514438 (Python Code)

Max Activating Token Index: 543

Text #17

Max Range: 2.8615. Min Range: -2.8615

Max Act: 1.9425. Min Act: -0.0000

Data Index: 1532851 (Python Code)

Max Activating Token Index: 113

Text #18

Max Range: 2.8615. Min Range: -2.8615

Max Act: 2.0368. Min Act: -0.0000

Data Index: 1560315 (Python Code)

Max Activating Token Index: 1017

Text #19

Max Range: 2.8615. Min Range: -2.8615

Max Act: 2.0469. Min Act: -0.0000

Data Index: 1436010 (Python Code)

Max Activating Token Index: 266