Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 475 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0548. Min Act: -0.0002

Data Index: 499901 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0496. Min Act: -0.0002

Data Index: 6217 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1029825 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1018133 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0423. Min Act: -0.0002

Data Index: 810928 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0438. Min Act: -0.0001

Data Index: 535779 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0450. Min Act: -0.0001

Data Index: 506361 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0400. Min Act: -0.0002

Data Index: 131785 (C4 (Web Text))

Max Activating Token Index: 949

Text #8

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0445. Min Act: -0.0002

Data Index: 31604 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0392. Min Act: -0.0001

Data Index: 316483 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0420. Min Act: -0.0001

Data Index: 185951 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0402. Min Act: -0.0002

Data Index: 312212 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0394. Min Act: -0.0002

Data Index: 190217 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0414. Min Act: -0.0002

Data Index: 227702 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0368. Min Act: -0.0002

Data Index: 72162 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1025191 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0389. Min Act: -0.0002

Data Index: 697891 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0371. Min Act: -0.0001

Data Index: 907828 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0400. Min Act: -0.0001

Data Index: 640726 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0370. Min Act: -0.0002

Data Index: 968726 (C4 (Web Text))

Max Activating Token Index: 375