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

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

Neuron 3938 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1630. Min Range: -1.1630

Max Act: 1.1630. Min Act: -0.0001

Data Index: 1374654 (Python Code)

Max Activating Token Index: 856

Text #1

Max Range: 1.1630. Min Range: -1.1630

Max Act: 1.0837. Min Act: -0.0001

Data Index: 448498 (C4 (Web Text))

Max Activating Token Index: 477

Text #2

Max Range: 1.1630. Min Range: -1.1630

Max Act: 1.0466. Min Act: -0.0001

Data Index: 1508723 (Python Code)

Max Activating Token Index: 184

Text #3

Max Range: 1.1630. Min Range: -1.1630

Max Act: 1.0903. Min Act: -0.0001

Data Index: 423559 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 1.1630. Min Range: -1.1630

Max Act: 1.0018. Min Act: -0.0001

Data Index: 365399 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 1.1630. Min Range: -1.1630

Max Act: 0.9996. Min Act: -0.0001

Data Index: 67428 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 1.1630. Min Range: -1.1630

Max Act: 1.0061. Min Act: -0.0001

Data Index: 257455 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 1.1630. Min Range: -1.1630

Max Act: 0.9808. Min Act: -0.0001

Data Index: 1375835 (Python Code)

Max Activating Token Index: 462

Text #8

Max Range: 1.1630. Min Range: -1.1630

Max Act: 0.9462. Min Act: -0.0001

Data Index: 9349 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 1.1630. Min Range: -1.1630

Max Act: 0.9554. Min Act: -0.0001

Data Index: 81982 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 1.1630. Min Range: -1.1630

Max Act: 0.9194. Min Act: -0.0001

Data Index: 1604710 (Python Code)

Max Activating Token Index: 543

Text #11

Max Range: 1.1630. Min Range: -1.1630

Max Act: 0.8677. Min Act: -0.0001

Data Index: 794027 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 1.1630. Min Range: -1.1630

Max Act: 0.9139. Min Act: -0.0001

Data Index: 1517907 (Python Code)

Max Activating Token Index: 653

Text #13

Max Range: 1.1630. Min Range: -1.1630

Max Act: 0.8775. Min Act: -0.0001

Data Index: 1564437 (Python Code)

Max Activating Token Index: 990

Text #14

Max Range: 1.1630. Min Range: -1.1630

Max Act: 0.7809. Min Act: -0.0001

Data Index: 1438876 (Python Code)

Max Activating Token Index: 733

Text #15

Max Range: 1.1630. Min Range: -1.1630

Max Act: 0.8547. Min Act: -0.0001

Data Index: 1517441 (Python Code)

Max Activating Token Index: 693

Text #16

Max Range: 1.1630. Min Range: -1.1630

Max Act: 0.8436. Min Act: -0.0001

Data Index: 572472 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 1.1630. Min Range: -1.1630

Max Act: 0.8451. Min Act: -0.0001

Data Index: 1064689 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 1.1630. Min Range: -1.1630

Max Act: 0.8437. Min Act: -0.0001

Data Index: 1175720 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 1.1630. Min Range: -1.1630

Max Act: 0.8349. Min Act: -0.0001

Data Index: 8679 (C4 (Web Text))

Max Activating Token Index: 50