Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1107 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0568. Min Act: -0.0003

Data Index: 1605169 (Python Code)

Max Activating Token Index: 148

Text #1

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0479. Min Act: -0.0003

Data Index: 1528629 (Python Code)

Max Activating Token Index: 346

Text #2

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0522. Min Act: -0.0003

Data Index: 317520 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0515. Min Act: -0.0003

Data Index: 119202 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0513. Min Act: -0.0004

Data Index: 1245810 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0479. Min Act: -0.0003

Data Index: 218368 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0473. Min Act: -0.0003

Data Index: 1512276 (Python Code)

Max Activating Token Index: 231

Text #7

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0491. Min Act: -0.0003

Data Index: 1123281 (C4 (Web Text))

Max Activating Token Index: 584

Text #8

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0501. Min Act: -0.0003

Data Index: 1397276 (Python Code)

Max Activating Token Index: 944

Text #9

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0461. Min Act: -0.0003

Data Index: 1405643 (Python Code)

Max Activating Token Index: 959

Text #10

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0474. Min Act: -0.0003

Data Index: 1212277 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0467. Min Act: -0.0003

Data Index: 1545604 (Python Code)

Max Activating Token Index: 277

Text #12

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0441. Min Act: -0.0003

Data Index: 788286 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0457. Min Act: -0.0002

Data Index: 858669 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0448. Min Act: -0.0003

Data Index: 1129250 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0474. Min Act: -0.0003

Data Index: 254464 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0476. Min Act: -0.0003

Data Index: 1641247 (Python Code)

Max Activating Token Index: 950

Text #17

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0435. Min Act: -0.0003

Data Index: 1537851 (Python Code)

Max Activating Token Index: 401

Text #18

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0427. Min Act: -0.0003

Data Index: 1521161 (Python Code)

Max Activating Token Index: 660

Text #19

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0438. Min Act: -0.0003

Data Index: 752064 (C4 (Web Text))

Max Activating Token Index: 282