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

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

Neuron 1593 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1997. Min Act: -0.0001

Data Index: 1535423 (Python Code)

Max Activating Token Index: 482

Text #1

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1769. Min Act: -0.0001

Data Index: 1175936 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1731. Min Act: -0.0001

Data Index: 1595125 (Python Code)

Max Activating Token Index: 582

Text #3

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1740. Min Act: -0.0001

Data Index: 369928 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1642. Min Act: -0.0001

Data Index: 1636140 (Python Code)

Max Activating Token Index: 394

Text #5

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1602. Min Act: -0.0001

Data Index: 101838 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1586. Min Act: -0.0002

Data Index: 81485 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1562. Min Act: -0.0002

Data Index: 1261396 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1486. Min Act: -0.0001

Data Index: 392518 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1518. Min Act: -0.0002

Data Index: 949778 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1513. Min Act: -0.0001

Data Index: 592682 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1498. Min Act: -0.0002

Data Index: 822249 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1451. Min Act: -0.0002

Data Index: 1310877 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1454. Min Act: -0.0002

Data Index: 416493 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1534. Min Act: -0.0001

Data Index: 520151 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1473. Min Act: -0.0002

Data Index: 292376 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1519. Min Act: -0.0002

Data Index: 701467 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1467. Min Act: -0.0002

Data Index: 1336174 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1524. Min Act: -0.0002

Data Index: 643768 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1466. Min Act: -0.0002

Data Index: 1191270 (C4 (Web Text))

Max Activating Token Index: 54