Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3085 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8763. Min Act: -0.0000

Data Index: 791832 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8643. Min Act: -0.0000

Data Index: 1593088 (Python Code)

Max Activating Token Index: 348

Text #2

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8575. Min Act: -0.0000

Data Index: 1380926 (Python Code)

Max Activating Token Index: 237

Text #3

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8979. Min Act: -0.0000

Data Index: 1365418 (Python Code)

Max Activating Token Index: 831

Text #4

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8056. Min Act: -0.0000

Data Index: 1409252 (Python Code)

Max Activating Token Index: 118

Text #5

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8310. Min Act: -0.0000

Data Index: 1588563 (Python Code)

Max Activating Token Index: 117

Text #6

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8606. Min Act: -0.0000

Data Index: 1609075 (Python Code)

Max Activating Token Index: 942

Text #7

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8025. Min Act: -0.0000

Data Index: 461693 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8236. Min Act: -0.0000

Data Index: 640761 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8049. Min Act: -0.0000

Data Index: 1027353 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7942. Min Act: -0.0000

Data Index: 1498806 (Python Code)

Max Activating Token Index: 53

Text #11

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7758. Min Act: -0.0000

Data Index: 1378085 (Python Code)

Max Activating Token Index: 53

Text #12

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7965. Min Act: -0.0000

Data Index: 684821 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7840. Min Act: -0.0000

Data Index: 1499136 (Python Code)

Max Activating Token Index: 317

Text #14

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7525. Min Act: -0.0000

Data Index: 1620832 (Python Code)

Max Activating Token Index: 608

Text #15

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7434. Min Act: -0.0000

Data Index: 828956 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7281. Min Act: -0.0000

Data Index: 188930 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7011. Min Act: -0.0000

Data Index: 1499282 (Python Code)

Max Activating Token Index: 746

Text #18

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.6641. Min Act: -0.0000

Data Index: 224587 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7098. Min Act: -0.0000

Data Index: 1644799 (Python Code)

Max Activating Token Index: 137