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

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

Neuron 1105 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0705. Min Act: -0.0004

Data Index: 92987 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0562. Min Act: -0.0004

Data Index: 939739 (C4 (Web Text))

Max Activating Token Index: 910

Text #2

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0565. Min Act: -0.0004

Data Index: 534260 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0701. Min Act: -0.0004

Data Index: 613761 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0571. Min Act: -0.0004

Data Index: 145304 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0637. Min Act: -0.0004

Data Index: 1258579 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0635. Min Act: -0.0004

Data Index: 388621 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0560. Min Act: -0.0004

Data Index: 914722 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0654. Min Act: -0.0004

Data Index: 402626 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0651. Min Act: -0.0004

Data Index: 623319 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0517. Min Act: -0.0004

Data Index: 1162250 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0602. Min Act: -0.0004

Data Index: 1326079 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0651. Min Act: -0.0004

Data Index: 1213417 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0600. Min Act: -0.0004

Data Index: 639888 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0593. Min Act: -0.0004

Data Index: 375831 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0579. Min Act: -0.0004

Data Index: 1282473 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0621. Min Act: -0.0004

Data Index: 449654 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0587. Min Act: -0.0004

Data Index: 233458 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0525. Min Act: -0.0004

Data Index: 864412 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0592. Min Act: -0.0004

Data Index: 594315 (C4 (Web Text))

Max Activating Token Index: 695