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

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

Neuron 753 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: 0.0736. Min Range: -0.0736

Max Act: 0.0736. Min Act: -0.0002

Data Index: 1178439 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0700. Min Act: -0.0001

Data Index: 566960 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0676. Min Act: -0.0002

Data Index: 466731 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0591. Min Act: -0.0002

Data Index: 272657 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0576. Min Act: -0.0001

Data Index: 1301038 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0557. Min Act: -0.0002

Data Index: 476464 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0522. Min Act: -0.0001

Data Index: 489330 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0554. Min Act: -0.0002

Data Index: 1015161 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0542. Min Act: -0.0002

Data Index: 923421 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1170106 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0591. Min Act: -0.0002

Data Index: 1314417 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0560. Min Act: -0.0002

Data Index: 431855 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0560. Min Act: -0.0002

Data Index: 409596 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0531. Min Act: -0.0002

Data Index: 364780 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0525. Min Act: -0.0002

Data Index: 970631 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0532. Min Act: -0.0002

Data Index: 77417 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0517. Min Act: -0.0002

Data Index: 965032 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0528. Min Act: -0.0002

Data Index: 1344059 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0506. Min Act: -0.0002

Data Index: 1134352 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0525. Min Act: -0.0002

Data Index: 923405 (C4 (Web Text))

Max Activating Token Index: 278