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

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

Neuron 1667 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1347. Min Act: -0.0000

Data Index: 1227059 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1318. Min Act: -0.0001

Data Index: 400472 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1250. Min Act: -0.0001

Data Index: 490631 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1263. Min Act: -0.0000

Data Index: 531188 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1200. Min Act: -0.0000

Data Index: 227825 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1182. Min Act: -0.0000

Data Index: 181384 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1138. Min Act: -0.0001

Data Index: 686825 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1119. Min Act: -0.0001

Data Index: 775962 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1096. Min Act: -0.0001

Data Index: 432103 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1093. Min Act: -0.0000

Data Index: 702275 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1090. Min Act: -0.0001

Data Index: 933681 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1033. Min Act: -0.0001

Data Index: 927244 (C4 (Web Text))

Max Activating Token Index: 266

Text #12

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1059. Min Act: -0.0001

Data Index: 280873 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1053. Min Act: -0.0001

Data Index: 1378210 (Python Code)

Max Activating Token Index: 756

Text #14

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1009. Min Act: -0.0000

Data Index: 679692 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1015. Min Act: -0.0000

Data Index: 1173146 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1020. Min Act: -0.0001

Data Index: 930001 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1011. Min Act: -0.0000

Data Index: 756646 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1041. Min Act: -0.0001

Data Index: 648350 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1004. Min Act: -0.0000

Data Index: 19793 (C4 (Web Text))

Max Activating Token Index: 210