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

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

Neuron 1940 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: 0.2690. Min Range: -0.2690

Max Act: 0.2540. Min Act: -0.0000

Data Index: 273301 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.2690. Min Act: -0.0001

Data Index: 1347541 (C4 (Web Text))

Max Activating Token Index: 541

Text #2

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.2159. Min Act: -0.0001

Data Index: 797756 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.1700. Min Act: -0.0001

Data Index: 1222664 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.2121. Min Act: -0.0001

Data Index: 573611 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.1976. Min Act: -0.0001

Data Index: 1340229 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.1996. Min Act: -0.0001

Data Index: 965710 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.1727. Min Act: -0.0001

Data Index: 42824 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.1635. Min Act: -0.0001

Data Index: 222152 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.1592. Min Act: -0.0001

Data Index: 1323803 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.1517. Min Act: -0.0000

Data Index: 1004035 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.1440. Min Act: -0.0001

Data Index: 79727 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.1335. Min Act: -0.0001

Data Index: 1188681 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.1283. Min Act: -0.0001

Data Index: 1071852 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.1266. Min Act: -0.0001

Data Index: 622506 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.1299. Min Act: -0.0000

Data Index: 1220039 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.1178. Min Act: -0.0001

Data Index: 1246017 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.1258. Min Act: -0.0001

Data Index: 1078236 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.1235. Min Act: -0.0001

Data Index: 390940 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.1166. Min Act: -0.0001

Data Index: 77508 (C4 (Web Text))

Max Activating Token Index: 595