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

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

Neuron 567 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2759. Min Act: -0.0000

Data Index: 1566542 (Python Code)

Max Activating Token Index: 621

Text #1

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2968. Min Act: -0.0000

Data Index: 1382233 (Python Code)

Max Activating Token Index: 914

Text #2

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2454. Min Act: -0.0000

Data Index: 1615073 (Python Code)

Max Activating Token Index: 627

Text #3

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2327. Min Act: -0.0000

Data Index: 1503739 (Python Code)

Max Activating Token Index: 856

Text #4

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2358. Min Act: -0.0000

Data Index: 1438439 (Python Code)

Max Activating Token Index: 942

Text #5

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2280. Min Act: -0.0000

Data Index: 1611379 (Python Code)

Max Activating Token Index: 180

Text #6

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2255. Min Act: -0.0000

Data Index: 1578303 (Python Code)

Max Activating Token Index: 481

Text #7

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2265. Min Act: -0.0000

Data Index: 1607972 (Python Code)

Max Activating Token Index: 230

Text #8

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2176. Min Act: -0.0000

Data Index: 1655831 (Python Code)

Max Activating Token Index: 273

Text #9

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2305. Min Act: -0.0000

Data Index: 1383072 (Python Code)

Max Activating Token Index: 362

Text #10

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2089. Min Act: -0.0000

Data Index: 1432713 (Python Code)

Max Activating Token Index: 931

Text #11

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2253. Min Act: -0.0000

Data Index: 1573620 (Python Code)

Max Activating Token Index: 293

Text #12

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2000. Min Act: -0.0000

Data Index: 1554713 (Python Code)

Max Activating Token Index: 331

Text #13

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2079. Min Act: -0.0000

Data Index: 1517470 (Python Code)

Max Activating Token Index: 575

Text #14

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2088. Min Act: -0.0000

Data Index: 1599526 (Python Code)

Max Activating Token Index: 408

Text #15

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.1914. Min Act: -0.0000

Data Index: 1630689 (Python Code)

Max Activating Token Index: 956

Text #16

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2060. Min Act: -0.0000

Data Index: 1432720 (Python Code)

Max Activating Token Index: 692

Text #17

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2137. Min Act: -0.0000

Data Index: 1495465 (Python Code)

Max Activating Token Index: 593

Text #18

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.1984. Min Act: -0.0000

Data Index: 1632647 (Python Code)

Max Activating Token Index: 173

Text #19

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2045. Min Act: -0.0000

Data Index: 1487149 (Python Code)

Max Activating Token Index: 569