Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 735 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1107481 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0515. Min Act: -0.0001

Data Index: 982962 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0500. Min Act: -0.0002

Data Index: 330088 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0470. Min Act: -0.0001

Data Index: 565050 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0470. Min Act: -0.0002

Data Index: 157522 (C4 (Web Text))

Max Activating Token Index: 477

Text #5

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0472. Min Act: -0.0002

Data Index: 416281 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0449. Min Act: -0.0002

Data Index: 737665 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0462. Min Act: -0.0002

Data Index: 743007 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0457. Min Act: -0.0002

Data Index: 918980 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0445. Min Act: -0.0002

Data Index: 994836 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0461. Min Act: -0.0002

Data Index: 358733 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0436. Min Act: -0.0002

Data Index: 645003 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0420. Min Act: -0.0002

Data Index: 676785 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0440. Min Act: -0.0002

Data Index: 403533 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1243769 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0452. Min Act: -0.0002

Data Index: 840489 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0421. Min Act: -0.0002

Data Index: 723520 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0437. Min Act: -0.0002

Data Index: 113574 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0417. Min Act: -0.0002

Data Index: 806180 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0411. Min Act: -0.0002

Data Index: 46203 (C4 (Web Text))

Max Activating Token Index: 741