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

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

Neuron 5865 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.2717. Min Act: -0.0000

Data Index: 804805 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.2402. Min Act: -0.0000

Data Index: 1444232 (Python Code)

Max Activating Token Index: 221

Text #2

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.1692. Min Act: -0.0000

Data Index: 1304531 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.1692. Min Act: -0.0000

Data Index: 682739 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.1394. Min Act: -0.0000

Data Index: 1496898 (Python Code)

Max Activating Token Index: 40

Text #5

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.1288. Min Act: -0.0000

Data Index: 1147434 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.1081. Min Act: -0.0000

Data Index: 1527567 (Python Code)

Max Activating Token Index: 44

Text #7

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.0929. Min Act: -0.0000

Data Index: 1452883 (Python Code)

Max Activating Token Index: 463

Text #8

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.0654. Min Act: -0.0000

Data Index: 1150107 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.0604. Min Act: -0.0000

Data Index: 1550602 (Python Code)

Max Activating Token Index: 400

Text #10

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.0209. Min Act: -0.0000

Data Index: 1626328 (Python Code)

Max Activating Token Index: 268

Text #11

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.0111. Min Act: -0.0000

Data Index: 172695 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.0139. Min Act: -0.0000

Data Index: 354669 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 1.2717. Min Range: -1.2717

Max Act: 0.9809. Min Act: -0.0000

Data Index: 428039 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 1.2717. Min Range: -1.2717

Max Act: 0.9847. Min Act: -0.0000

Data Index: 564644 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 1.2717. Min Range: -1.2717

Max Act: 0.9336. Min Act: -0.0000

Data Index: 1096425 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 1.2717. Min Range: -1.2717

Max Act: 0.9538. Min Act: -0.0000

Data Index: 1434032 (Python Code)

Max Activating Token Index: 431

Text #17

Max Range: 1.2717. Min Range: -1.2717

Max Act: 0.9169. Min Act: -0.0000

Data Index: 217945 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 1.2717. Min Range: -1.2717

Max Act: 0.9387. Min Act: -0.0000

Data Index: 1371321 (Python Code)

Max Activating Token Index: 650

Text #19

Max Range: 1.2717. Min Range: -1.2717

Max Act: 0.9115. Min Act: -0.0000

Data Index: 1618028 (Python Code)

Max Activating Token Index: 733