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

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

Neuron 3980 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1304. Min Act: -0.0001

Data Index: 756841 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1191. Min Act: -0.0001

Data Index: 1473076 (Python Code)

Max Activating Token Index: 3

Text #2

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1208. Min Act: -0.0001

Data Index: 970888 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1183. Min Act: -0.0001

Data Index: 1268730 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1105. Min Act: -0.0001

Data Index: 818006 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1036. Min Act: -0.0001

Data Index: 687059 (C4 (Web Text))

Max Activating Token Index: 747

Text #6

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1006. Min Act: -0.0001

Data Index: 349050 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0654. Min Act: -0.0001

Data Index: 1533797 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0909. Min Act: -0.0001

Data Index: 1613694 (Python Code)

Max Activating Token Index: 797

Text #9

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1046. Min Act: -0.0001

Data Index: 199857 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1007. Min Act: -0.0001

Data Index: 1120364 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0901. Min Act: -0.0001

Data Index: 1173521 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0914. Min Act: -0.0001

Data Index: 1083072 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0852. Min Act: -0.0001

Data Index: 545647 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0978. Min Act: -0.0001

Data Index: 1319601 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0947. Min Act: -0.0001

Data Index: 957121 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0985. Min Act: -0.0001

Data Index: 809956 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0847. Min Act: -0.0001

Data Index: 302366 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0953. Min Act: -0.0001

Data Index: 1508655 (Python Code)

Max Activating Token Index: 397

Text #19

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0969. Min Act: -0.0001

Data Index: 1226762 (C4 (Web Text))

Max Activating Token Index: 491