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

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

Neuron 3351 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: 0.1450. Min Range: -0.1450

Max Act: 0.1450. Min Act: -0.0001

Data Index: 662080 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1337. Min Act: -0.0001

Data Index: 1054367 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1361. Min Act: -0.0000

Data Index: 136665 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1347. Min Act: -0.0001

Data Index: 1301292 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1222. Min Act: -0.0001

Data Index: 511611 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1182. Min Act: -0.0001

Data Index: 963114 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1237. Min Act: -0.0000

Data Index: 1001621 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1237. Min Act: -0.0001

Data Index: 847302 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1208. Min Act: -0.0001

Data Index: 1129534 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1217. Min Act: -0.0001

Data Index: 91323 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1084. Min Act: -0.0001

Data Index: 515543 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1034. Min Act: -0.0001

Data Index: 1077224 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1134. Min Act: -0.0000

Data Index: 831494 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1058. Min Act: -0.0000

Data Index: 63611 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.0989. Min Act: -0.0000

Data Index: 1172140 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1014. Min Act: -0.0001

Data Index: 1084505 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1072. Min Act: -0.0001

Data Index: 105145 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1081. Min Act: -0.0000

Data Index: 1283081 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1082. Min Act: -0.0000

Data Index: 950521 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1147. Min Act: -0.0000

Data Index: 49015 (C4 (Web Text))

Max Activating Token Index: 970