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

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

Neuron 4710 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9438. Min Range: -2.9438

Max Act: 2.9438. Min Act: -0.0000

Data Index: 552099 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 2.9438. Min Range: -2.9438

Max Act: 2.1735. Min Act: 0.0000

Data Index: 481327 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 2.9438. Min Range: -2.9438

Max Act: 2.1115. Min Act: -0.0000

Data Index: 98520 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 2.9438. Min Range: -2.9438

Max Act: 1.9789. Min Act: 0.0000

Data Index: 1303188 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 2.9438. Min Range: -2.9438

Max Act: 2.0741. Min Act: -0.0000

Data Index: 1024357 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 2.9438. Min Range: -2.9438

Max Act: 1.9768. Min Act: -0.0000

Data Index: 69749 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 2.9438. Min Range: -2.9438

Max Act: 1.9721. Min Act: -0.0000

Data Index: 1076017 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 2.9438. Min Range: -2.9438

Max Act: 1.8675. Min Act: -0.0000

Data Index: 873093 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 2.9438. Min Range: -2.9438

Max Act: 1.9983. Min Act: 0.0000

Data Index: 1460196 (Python Code)

Max Activating Token Index: 824

Text #9

Max Range: 2.9438. Min Range: -2.9438

Max Act: 2.0680. Min Act: -0.0000

Data Index: 57851 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 2.9438. Min Range: -2.9438

Max Act: 1.9369. Min Act: -0.0000

Data Index: 1231705 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 2.9438. Min Range: -2.9438

Max Act: 1.8987. Min Act: 0.0000

Data Index: 1589657 (Python Code)

Max Activating Token Index: 782

Text #12

Max Range: 2.9438. Min Range: -2.9438

Max Act: 1.7831. Min Act: 0.0000

Data Index: 997413 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 2.9438. Min Range: -2.9438

Max Act: 1.9629. Min Act: -0.0000

Data Index: 1271068 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 2.9438. Min Range: -2.9438

Max Act: 1.6966. Min Act: -0.0000

Data Index: 286037 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 2.9438. Min Range: -2.9438

Max Act: 1.6749. Min Act: 0.0000

Data Index: 525570 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 2.9438. Min Range: -2.9438

Max Act: 1.7799. Min Act: -0.0000

Data Index: 1413309 (Python Code)

Max Activating Token Index: 154

Text #17

Max Range: 2.9438. Min Range: -2.9438

Max Act: 1.7696. Min Act: -0.0000

Data Index: 548229 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 2.9438. Min Range: -2.9438

Max Act: 1.7600. Min Act: -0.0000

Data Index: 1621482 (Python Code)

Max Activating Token Index: 650

Text #19

Max Range: 2.9438. Min Range: -2.9438

Max Act: 1.8345. Min Act: 0.0000

Data Index: 406684 (C4 (Web Text))

Max Activating Token Index: 681