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

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

Neuron 2768 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: 0.2159. Min Range: -0.2159

Max Act: 0.2159. Min Act: -0.0001

Data Index: 970424 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.2126. Min Act: -0.0001

Data Index: 162662 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.2104. Min Act: -0.0001

Data Index: 484913 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1866. Min Act: -0.0001

Data Index: 167731 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1489. Min Act: -0.0001

Data Index: 1387311 (Python Code)

Max Activating Token Index: 977

Text #5

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1502. Min Act: -0.0001

Data Index: 744578 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1450. Min Act: -0.0001

Data Index: 485302 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1502. Min Act: -0.0000

Data Index: 374554 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1374. Min Act: -0.0000

Data Index: 1021569 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1240. Min Act: -0.0001

Data Index: 110277 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1476. Min Act: -0.0001

Data Index: 87843 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1484. Min Act: -0.0001

Data Index: 20704 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1318. Min Act: -0.0001

Data Index: 19327 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1287. Min Act: -0.0001

Data Index: 1597921 (Python Code)

Max Activating Token Index: 252

Text #14

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1221. Min Act: -0.0000

Data Index: 1267224 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1292. Min Act: -0.0001

Data Index: 1159205 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1266. Min Act: -0.0001

Data Index: 1646564 (Python Code)

Max Activating Token Index: 777

Text #17

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1269. Min Act: -0.0001

Data Index: 1233895 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1286. Min Act: -0.0000

Data Index: 1149785 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1240. Min Act: -0.0001

Data Index: 21314 (C4 (Web Text))

Max Activating Token Index: 56