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

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

Neuron 3607 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0557. Min Act: -0.0003

Data Index: 326779 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0599. Min Act: -0.0004

Data Index: 170222 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0557. Min Act: -0.0003

Data Index: 1181632 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0618. Min Act: -0.0004

Data Index: 711337 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0544. Min Act: -0.0003

Data Index: 366617 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0559. Min Act: -0.0003

Data Index: 732340 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0579. Min Act: -0.0003

Data Index: 1302062 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0518. Min Act: -0.0003

Data Index: 156704 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0553. Min Act: -0.0003

Data Index: 1338304 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0513. Min Act: -0.0003

Data Index: 1263001 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0547. Min Act: -0.0003

Data Index: 950107 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0543. Min Act: -0.0003

Data Index: 1126734 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0559. Min Act: -0.0003

Data Index: 921889 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0542. Min Act: -0.0003

Data Index: 420302 (C4 (Web Text))

Max Activating Token Index: 343

Text #14

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0488. Min Act: -0.0003

Data Index: 547290 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0538. Min Act: -0.0004

Data Index: 686679 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0520. Min Act: -0.0003

Data Index: 1270215 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0519. Min Act: -0.0003

Data Index: 426792 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0497. Min Act: -0.0003

Data Index: 70149 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0489. Min Act: -0.0003

Data Index: 1269513 (C4 (Web Text))

Max Activating Token Index: 931