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

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

Neuron 1956 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.2257. Min Act: -0.0000

Data Index: 1621984 (Python Code)

Max Activating Token Index: 89

Text #1

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.2173. Min Act: -0.0001

Data Index: 1416931 (Python Code)

Max Activating Token Index: 378

Text #2

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.2032. Min Act: -0.0000

Data Index: 1507954 (Python Code)

Max Activating Token Index: 965

Text #3

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1944. Min Act: -0.0000

Data Index: 1619129 (Python Code)

Max Activating Token Index: 153

Text #4

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1986. Min Act: -0.0000

Data Index: 1561188 (Python Code)

Max Activating Token Index: 503

Text #5

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1996. Min Act: 0.0000

Data Index: 1595474 (Python Code)

Max Activating Token Index: 429

Text #6

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.2100. Min Act: -0.0000

Data Index: 1652149 (Python Code)

Max Activating Token Index: 79

Text #7

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1942. Min Act: 0.0001

Data Index: 1589111 (Python Code)

Max Activating Token Index: 99

Text #8

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1962. Min Act: -0.0000

Data Index: 1653315 (Python Code)

Max Activating Token Index: 378

Text #9

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1926. Min Act: -0.0000

Data Index: 458098 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1803. Min Act: -0.0000

Data Index: 1474632 (Python Code)

Max Activating Token Index: 432

Text #11

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1846. Min Act: -0.0000

Data Index: 1432988 (Python Code)

Max Activating Token Index: 188

Text #12

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1826. Min Act: -0.0001

Data Index: 1477702 (Python Code)

Max Activating Token Index: 253

Text #13

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1819. Min Act: -0.0000

Data Index: 1515186 (Python Code)

Max Activating Token Index: 820

Text #14

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1809. Min Act: -0.0000

Data Index: 1534141 (Python Code)

Max Activating Token Index: 142

Text #15

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1795. Min Act: -0.0000

Data Index: 1385273 (Python Code)

Max Activating Token Index: 104

Text #16

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1773. Min Act: -0.0000

Data Index: 1376233 (Python Code)

Max Activating Token Index: 134

Text #17

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1767. Min Act: -0.0000

Data Index: 1541617 (Python Code)

Max Activating Token Index: 962

Text #18

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1669. Min Act: -0.0000

Data Index: 1426172 (Python Code)

Max Activating Token Index: 633

Text #19

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1676. Min Act: -0.0000

Data Index: 1461820 (Python Code)

Max Activating Token Index: 126