Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2517 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0962. Min Act: -0.0000

Data Index: 412675 (C4 (Web Text))

Max Activating Token Index: 820

Text #1

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0556. Min Act: -0.0000

Data Index: 878867 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0526. Min Act: -0.0000

Data Index: 163076 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0559. Min Act: -0.0001

Data Index: 418439 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0569. Min Act: -0.0000

Data Index: 1141998 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0416. Min Act: -0.0000

Data Index: 1437200 (Python Code)

Max Activating Token Index: 263

Text #6

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0495. Min Act: -0.0000

Data Index: 231856 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0487. Min Act: -0.0000

Data Index: 199490 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0492. Min Act: -0.0000

Data Index: 392477 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0484. Min Act: -0.0000

Data Index: 991778 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0501. Min Act: -0.0000

Data Index: 1048676 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0464. Min Act: -0.0000

Data Index: 893199 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0476. Min Act: -0.0001

Data Index: 141169 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0481. Min Act: -0.0000

Data Index: 684385 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0455. Min Act: -0.0000

Data Index: 750434 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0488. Min Act: -0.0000

Data Index: 340390 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0466. Min Act: -0.0000

Data Index: 197353 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0468. Min Act: -0.0000

Data Index: 1485200 (Python Code)

Max Activating Token Index: 432

Text #18

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0512. Min Act: -0.0000

Data Index: 1062666 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0510. Min Act: -0.0000

Data Index: 1317447 (C4 (Web Text))

Max Activating Token Index: 41