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

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

Neuron 68 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: 0.0787. Min Range: -0.0787

Max Act: 0.0787. Min Act: -0.0002

Data Index: 254019 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0715. Min Act: -0.0002

Data Index: 255633 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0731. Min Act: -0.0001

Data Index: 509823 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0699. Min Act: -0.0002

Data Index: 35109 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0650. Min Act: -0.0002

Data Index: 1111130 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0687. Min Act: -0.0001

Data Index: 356760 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0680. Min Act: -0.0001

Data Index: 705755 (C4 (Web Text))

Max Activating Token Index: 523

Text #7

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0702. Min Act: -0.0001

Data Index: 997077 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0667. Min Act: -0.0002

Data Index: 736046 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0643. Min Act: -0.0002

Data Index: 1008453 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0646. Min Act: -0.0002

Data Index: 178073 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0626. Min Act: -0.0002

Data Index: 448440 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0655. Min Act: -0.0002

Data Index: 103925 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0626. Min Act: -0.0002

Data Index: 398795 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0589. Min Act: -0.0002

Data Index: 418563 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0650. Min Act: -0.0002

Data Index: 102173 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0606. Min Act: -0.0001

Data Index: 1195967 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0648. Min Act: -0.0002

Data Index: 1263440 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0647. Min Act: -0.0001

Data Index: 1260199 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0643. Min Act: -0.0002

Data Index: 236492 (C4 (Web Text))

Max Activating Token Index: 799