Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1480 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0523. Min Act: -0.0003

Data Index: 654220 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0536. Min Act: -0.0003

Data Index: 302631 (C4 (Web Text))

Max Activating Token Index: 334

Text #2

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0523. Min Act: -0.0002

Data Index: 502877 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0531. Min Act: -0.0003

Data Index: 484048 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0499. Min Act: -0.0003

Data Index: 836540 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0535. Min Act: -0.0003

Data Index: 444063 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0473. Min Act: -0.0004

Data Index: 561584 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0468. Min Act: -0.0003

Data Index: 904490 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0461. Min Act: -0.0003

Data Index: 137854 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0456. Min Act: -0.0003

Data Index: 862124 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0455. Min Act: -0.0003

Data Index: 1052479 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0482. Min Act: -0.0003

Data Index: 1646300 (Python Code)

Max Activating Token Index: 1008

Text #12

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0455. Min Act: -0.0003

Data Index: 1243539 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0459. Min Act: -0.0003

Data Index: 988722 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0463. Min Act: -0.0003

Data Index: 419060 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0461. Min Act: -0.0003

Data Index: 711615 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0449. Min Act: -0.0004

Data Index: 33917 (C4 (Web Text))

Max Activating Token Index: 129

Text #17

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0465. Min Act: -0.0003

Data Index: 563830 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0474. Min Act: -0.0003

Data Index: 403285 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0471. Min Act: -0.0003

Data Index: 639055 (C4 (Web Text))

Max Activating Token Index: 729