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

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

Neuron 4890 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4775. Min Range: -2.4775

Max Act: 2.4775. Min Act: -0.0000

Data Index: 882184 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 2.4775. Min Range: -2.4775

Max Act: 2.1763. Min Act: -0.0000

Data Index: 995050 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 2.4775. Min Range: -2.4775

Max Act: 2.0020. Min Act: -0.0000

Data Index: 992747 (C4 (Web Text))

Max Activating Token Index: 325

Text #3

Max Range: 2.4775. Min Range: -2.4775

Max Act: 1.9937. Min Act: -0.0000

Data Index: 789182 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 2.4775. Min Range: -2.4775

Max Act: 2.0469. Min Act: -0.0000

Data Index: 326183 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 2.4775. Min Range: -2.4775

Max Act: 2.1658. Min Act: -0.0000

Data Index: 405256 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 2.4775. Min Range: -2.4775

Max Act: 2.0360. Min Act: -0.0000

Data Index: 1263522 (C4 (Web Text))

Max Activating Token Index: 462

Text #7

Max Range: 2.4775. Min Range: -2.4775

Max Act: 1.9659. Min Act: -0.0000

Data Index: 857112 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 2.4775. Min Range: -2.4775

Max Act: 1.9348. Min Act: -0.0000

Data Index: 1117512 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 2.4775. Min Range: -2.4775

Max Act: 1.9012. Min Act: -0.0000

Data Index: 320627 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 2.4775. Min Range: -2.4775

Max Act: 1.9550. Min Act: -0.0000

Data Index: 112527 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 2.4775. Min Range: -2.4775

Max Act: 1.7879. Min Act: -0.0000

Data Index: 1214461 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 2.4775. Min Range: -2.4775

Max Act: 1.8933. Min Act: -0.0000

Data Index: 1361253 (Python Code)

Max Activating Token Index: 942

Text #13

Max Range: 2.4775. Min Range: -2.4775

Max Act: 1.6899. Min Act: -0.0000

Data Index: 1027893 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 2.4775. Min Range: -2.4775

Max Act: 1.7858. Min Act: -0.0000

Data Index: 96022 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 2.4775. Min Range: -2.4775

Max Act: 1.7803. Min Act: -0.0000

Data Index: 1229919 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 2.4775. Min Range: -2.4775

Max Act: 1.7656. Min Act: -0.0000

Data Index: 587025 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 2.4775. Min Range: -2.4775

Max Act: 1.7465. Min Act: -0.0000

Data Index: 238127 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 2.4775. Min Range: -2.4775

Max Act: 1.7634. Min Act: -0.0000

Data Index: 440963 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 2.4775. Min Range: -2.4775

Max Act: 1.7515. Min Act: -0.0000

Data Index: 267419 (C4 (Web Text))

Max Activating Token Index: 81