Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2184 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.7288. Min Act: -0.0001

Data Index: 1034160 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.7422. Min Act: -0.0001

Data Index: 1179133 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.7450. Min Act: -0.0001

Data Index: 1218712 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.7099. Min Act: -0.0001

Data Index: 143548 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.7176. Min Act: -0.0001

Data Index: 1197631 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.7107. Min Act: -0.0001

Data Index: 996032 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.6988. Min Act: -0.0001

Data Index: 311478 (C4 (Web Text))

Max Activating Token Index: 924

Text #7

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.6583. Min Act: -0.0001

Data Index: 246224 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.7154. Min Act: -0.0001

Data Index: 451562 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.6902. Min Act: -0.0001

Data Index: 1275668 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.6716. Min Act: -0.0001

Data Index: 1006117 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.6941. Min Act: -0.0001

Data Index: 262818 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.6644. Min Act: -0.0001

Data Index: 202043 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.6871. Min Act: -0.0001

Data Index: 332690 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.6594. Min Act: -0.0001

Data Index: 975394 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.6614. Min Act: -0.0001

Data Index: 882236 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.6454. Min Act: -0.0001

Data Index: 892454 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.6086. Min Act: -0.0001

Data Index: 1303211 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.6653. Min Act: -0.0001

Data Index: 1547916 (Python Code)

Max Activating Token Index: 938

Text #19

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.6415. Min Act: -0.0001

Data Index: 1119212 (C4 (Web Text))

Max Activating Token Index: 788