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

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

Neuron 4473 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2771. Min Act: -0.0001

Data Index: 1508199 (Python Code)

Max Activating Token Index: 142

Text #1

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2736. Min Act: -0.0001

Data Index: 1435251 (Python Code)

Max Activating Token Index: 768

Text #2

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2630. Min Act: -0.0001

Data Index: 1382824 (Python Code)

Max Activating Token Index: 985

Text #3

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2511. Min Act: -0.0001

Data Index: 1602378 (Python Code)

Max Activating Token Index: 667

Text #4

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2464. Min Act: -0.0001

Data Index: 1575124 (Python Code)

Max Activating Token Index: 402

Text #5

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2281. Min Act: -0.0001

Data Index: 1495167 (Python Code)

Max Activating Token Index: 954

Text #6

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2302. Min Act: -0.0001

Data Index: 1539768 (Python Code)

Max Activating Token Index: 443

Text #7

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2127. Min Act: -0.0001

Data Index: 1499124 (Python Code)

Max Activating Token Index: 185

Text #8

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2204. Min Act: -0.0001

Data Index: 786321 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2137. Min Act: -0.0001

Data Index: 1503728 (Python Code)

Max Activating Token Index: 59

Text #10

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2073. Min Act: -0.0001

Data Index: 1586818 (Python Code)

Max Activating Token Index: 878

Text #11

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2003. Min Act: -0.0001

Data Index: 1554892 (Python Code)

Max Activating Token Index: 562

Text #12

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2058. Min Act: -0.0001

Data Index: 1499580 (Python Code)

Max Activating Token Index: 158

Text #13

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.1990. Min Act: -0.0001

Data Index: 1575964 (Python Code)

Max Activating Token Index: 204

Text #14

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.1909. Min Act: -0.0001

Data Index: 1577425 (Python Code)

Max Activating Token Index: 72

Text #15

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.1849. Min Act: -0.0001

Data Index: 1542855 (Python Code)

Max Activating Token Index: 935

Text #16

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2069. Min Act: -0.0001

Data Index: 1612888 (Python Code)

Max Activating Token Index: 834

Text #17

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.1935. Min Act: -0.0001

Data Index: 1496000 (Python Code)

Max Activating Token Index: 307

Text #18

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2134. Min Act: -0.0001

Data Index: 1361407 (Python Code)

Max Activating Token Index: 88

Text #19

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.1920. Min Act: -0.0001

Data Index: 1546272 (Python Code)

Max Activating Token Index: 337