Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 904 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0722. Min Act: -0.0003

Data Index: 1173306 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0617. Min Act: -0.0003

Data Index: 610429 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0613. Min Act: -0.0003

Data Index: 645785 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0596. Min Act: -0.0002

Data Index: 846085 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0519. Min Act: -0.0003

Data Index: 423797 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0508. Min Act: -0.0002

Data Index: 675468 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0469. Min Act: -0.0002

Data Index: 607251 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1111099 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0452. Min Act: -0.0003

Data Index: 413204 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0438. Min Act: -0.0002

Data Index: 1044588 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0433. Min Act: -0.0002

Data Index: 915502 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0455. Min Act: -0.0003

Data Index: 1221479 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0444. Min Act: -0.0003

Data Index: 906776 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0417. Min Act: -0.0003

Data Index: 1327255 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0416. Min Act: -0.0003

Data Index: 852796 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0405. Min Act: -0.0003

Data Index: 741798 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0413. Min Act: -0.0003

Data Index: 937256 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0392. Min Act: -0.0002

Data Index: 329982 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0400. Min Act: -0.0003

Data Index: 756846 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0395. Min Act: -0.0002

Data Index: 175668 (C4 (Web Text))

Max Activating Token Index: 618