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

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

Neuron 3054 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0993. Min Act: -0.0002

Data Index: 564200 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0625. Min Act: -0.0002

Data Index: 1148195 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0553. Min Act: -0.0002

Data Index: 933670 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0566. Min Act: -0.0002

Data Index: 990315 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0530. Min Act: -0.0002

Data Index: 667437 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0531. Min Act: -0.0002

Data Index: 1475169 (Python Code)

Max Activating Token Index: 746

Text #6

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0522. Min Act: -0.0002

Data Index: 985994 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0495. Min Act: -0.0002

Data Index: 1378161 (Python Code)

Max Activating Token Index: 171

Text #8

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0487. Min Act: -0.0002

Data Index: 38973 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0499. Min Act: -0.0002

Data Index: 661008 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1573282 (Python Code)

Max Activating Token Index: 478

Text #11

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0478. Min Act: -0.0002

Data Index: 1322056 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1171487 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0461. Min Act: -0.0002

Data Index: 1394297 (Python Code)

Max Activating Token Index: 582

Text #14

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0481. Min Act: -0.0002

Data Index: 1552059 (Python Code)

Max Activating Token Index: 792

Text #15

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0460. Min Act: -0.0002

Data Index: 673862 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0483. Min Act: -0.0002

Data Index: 1420281 (Python Code)

Max Activating Token Index: 383

Text #17

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0450. Min Act: -0.0002

Data Index: 1460248 (Python Code)

Max Activating Token Index: 310

Text #18

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0457. Min Act: -0.0002

Data Index: 1322482 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0456. Min Act: -0.0002

Data Index: 169619 (C4 (Web Text))

Max Activating Token Index: 426