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

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

Neuron 2984 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0974. Min Range: -3.0974

Max Act: 3.0974. Min Act: -0.0001

Data Index: 782709 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 3.0974. Min Range: -3.0974

Max Act: 1.8873. Min Act: -0.0001

Data Index: 344061 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 3.0974. Min Range: -3.0974

Max Act: 1.9591. Min Act: -0.0001

Data Index: 1449974 (Python Code)

Max Activating Token Index: 443

Text #3

Max Range: 3.0974. Min Range: -3.0974

Max Act: 1.7644. Min Act: -0.0000

Data Index: 688426 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 3.0974. Min Range: -3.0974

Max Act: 1.7506. Min Act: -0.0001

Data Index: 1270741 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 3.0974. Min Range: -3.0974

Max Act: 1.7588. Min Act: -0.0001

Data Index: 325821 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 3.0974. Min Range: -3.0974

Max Act: 1.6395. Min Act: -0.0001

Data Index: 40317 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 3.0974. Min Range: -3.0974

Max Act: 1.6634. Min Act: -0.0001

Data Index: 54961 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 3.0974. Min Range: -3.0974

Max Act: 1.6686. Min Act: -0.0001

Data Index: 918717 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 3.0974. Min Range: -3.0974

Max Act: 1.6699. Min Act: -0.0001

Data Index: 1050288 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 3.0974. Min Range: -3.0974

Max Act: 1.7646. Min Act: -0.0001

Data Index: 1011565 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 3.0974. Min Range: -3.0974

Max Act: 1.6278. Min Act: -0.0001

Data Index: 434413 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 3.0974. Min Range: -3.0974

Max Act: 1.6921. Min Act: -0.0001

Data Index: 312080 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 3.0974. Min Range: -3.0974

Max Act: 1.6601. Min Act: -0.0001

Data Index: 350008 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 3.0974. Min Range: -3.0974

Max Act: 1.5753. Min Act: -0.0001

Data Index: 1301090 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 3.0974. Min Range: -3.0974

Max Act: 1.3994. Min Act: -0.0001

Data Index: 885294 (C4 (Web Text))

Max Activating Token Index: 723

Text #16

Max Range: 3.0974. Min Range: -3.0974

Max Act: 1.6412. Min Act: -0.0001

Data Index: 843764 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 3.0974. Min Range: -3.0974

Max Act: 1.5456. Min Act: -0.0000

Data Index: 527437 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 3.0974. Min Range: -3.0974

Max Act: 1.5391. Min Act: -0.0001

Data Index: 111275 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 3.0974. Min Range: -3.0974

Max Act: 1.5335. Min Act: -0.0001

Data Index: 586358 (C4 (Web Text))

Max Activating Token Index: 199