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

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

Neuron 4222 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: 0.1610. Min Range: -0.1610

Max Act: 0.1610. Min Act: -0.0001

Data Index: 1365861 (Python Code)

Max Activating Token Index: 2

Text #1

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1418. Min Act: -0.0001

Data Index: 1531171 (Python Code)

Max Activating Token Index: 23

Text #2

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1220. Min Act: -0.0001

Data Index: 1649299 (Python Code)

Max Activating Token Index: 2

Text #3

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1183. Min Act: -0.0001

Data Index: 1387705 (Python Code)

Max Activating Token Index: 2

Text #4

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1207. Min Act: -0.0001

Data Index: 1406022 (Python Code)

Max Activating Token Index: 3

Text #5

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1218. Min Act: -0.0001

Data Index: 1429636 (Python Code)

Max Activating Token Index: 3

Text #6

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1211. Min Act: -0.0001

Data Index: 1508742 (Python Code)

Max Activating Token Index: 2

Text #7

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1234. Min Act: -0.0001

Data Index: 1472138 (Python Code)

Max Activating Token Index: 3

Text #8

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1234. Min Act: -0.0001

Data Index: 1393563 (Python Code)

Max Activating Token Index: 3

Text #9

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1234. Min Act: -0.0001

Data Index: 1617084 (Python Code)

Max Activating Token Index: 3

Text #10

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1234. Min Act: -0.0001

Data Index: 1558885 (Python Code)

Max Activating Token Index: 3

Text #11

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1187. Min Act: -0.0001

Data Index: 1564264 (Python Code)

Max Activating Token Index: 3

Text #12

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1135. Min Act: -0.0001

Data Index: 298447 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1075. Min Act: -0.0001

Data Index: 1565714 (Python Code)

Max Activating Token Index: 3

Text #14

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1032. Min Act: -0.0001

Data Index: 1583880 (Python Code)

Max Activating Token Index: 3

Text #15

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1107. Min Act: -0.0001

Data Index: 1496871 (Python Code)

Max Activating Token Index: 4

Text #16

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1064. Min Act: -0.0001

Data Index: 1387545 (Python Code)

Max Activating Token Index: 4

Text #17

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1078. Min Act: -0.0001

Data Index: 1559660 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1078. Min Act: -0.0001

Data Index: 1449244 (Python Code)

Max Activating Token Index: 4

Text #19

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1078. Min Act: -0.0001

Data Index: 1370092 (Python Code)

Max Activating Token Index: 4