Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1291 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.9457. Min Act: -0.0001

Data Index: 724493 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.9547. Min Act: -0.0001

Data Index: 1402409 (Python Code)

Max Activating Token Index: 25

Text #2

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.8518. Min Act: -0.0001

Data Index: 1435708 (Python Code)

Max Activating Token Index: 27

Text #3

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.9057. Min Act: -0.0001

Data Index: 1362261 (Python Code)

Max Activating Token Index: 17

Text #4

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.8139. Min Act: -0.0001

Data Index: 1499522 (Python Code)

Max Activating Token Index: 936

Text #5

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.9095. Min Act: -0.0001

Data Index: 1369500 (Python Code)

Max Activating Token Index: 906

Text #6

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.8897. Min Act: -0.0001

Data Index: 1456231 (Python Code)

Max Activating Token Index: 77

Text #7

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.8123. Min Act: -0.0001

Data Index: 1617689 (Python Code)

Max Activating Token Index: 7

Text #8

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.8323. Min Act: -0.0001

Data Index: 1654403 (Python Code)

Max Activating Token Index: 10

Text #9

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.8578. Min Act: -0.0001

Data Index: 1448658 (Python Code)

Max Activating Token Index: 28

Text #10

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.7917. Min Act: -0.0001

Data Index: 1436030 (Python Code)

Max Activating Token Index: 233

Text #11

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.8030. Min Act: -0.0001

Data Index: 1606459 (Python Code)

Max Activating Token Index: 533

Text #12

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.7755. Min Act: -0.0001

Data Index: 1541887 (Python Code)

Max Activating Token Index: 458

Text #13

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.8233. Min Act: -0.0001

Data Index: 1655261 (Python Code)

Max Activating Token Index: 73

Text #14

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.8232. Min Act: -0.0001

Data Index: 1372016 (Python Code)

Max Activating Token Index: 510

Text #15

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.8257. Min Act: -0.0001

Data Index: 1630739 (Python Code)

Max Activating Token Index: 456

Text #16

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.7568. Min Act: -0.0001

Data Index: 1654930 (Python Code)

Max Activating Token Index: 922

Text #17

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.7937. Min Act: -0.0001

Data Index: 1440676 (Python Code)

Max Activating Token Index: 636

Text #18

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.7477. Min Act: -0.0001

Data Index: 1627208 (Python Code)

Max Activating Token Index: 40

Text #19

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.7629. Min Act: -0.0001

Data Index: 1611241 (Python Code)

Max Activating Token Index: 79