Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2031 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0662. Min Act: -0.0003

Data Index: 819404 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0600. Min Act: -0.0003

Data Index: 151255 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0590. Min Act: -0.0003

Data Index: 698351 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0565. Min Act: -0.0003

Data Index: 1164004 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0518. Min Act: -0.0003

Data Index: 1435361 (Python Code)

Max Activating Token Index: 165

Text #5

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0515. Min Act: -0.0003

Data Index: 1278802 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0545. Min Act: -0.0003

Data Index: 404876 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0514. Min Act: -0.0003

Data Index: 1508172 (Python Code)

Max Activating Token Index: 455

Text #8

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0504. Min Act: -0.0003

Data Index: 86487 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0486. Min Act: -0.0003

Data Index: 1500033 (Python Code)

Max Activating Token Index: 794

Text #10

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0504. Min Act: -0.0003

Data Index: 1514292 (Python Code)

Max Activating Token Index: 826

Text #11

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0464. Min Act: -0.0003

Data Index: 37922 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0471. Min Act: -0.0003

Data Index: 1153190 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0470. Min Act: -0.0003

Data Index: 1402282 (Python Code)

Max Activating Token Index: 515

Text #14

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0448. Min Act: -0.0003

Data Index: 1642368 (Python Code)

Max Activating Token Index: 881

Text #15

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0464. Min Act: -0.0003

Data Index: 761085 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0479. Min Act: -0.0003

Data Index: 792594 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0456. Min Act: -0.0003

Data Index: 1577056 (Python Code)

Max Activating Token Index: 5

Text #18

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0462. Min Act: -0.0003

Data Index: 966525 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0459. Min Act: -0.0003

Data Index: 375907 (C4 (Web Text))

Max Activating Token Index: 424