Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 644 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0543. Min Act: -0.0006

Data Index: 1181277 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0499. Min Act: -0.0006

Data Index: 1024271 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0444. Min Act: -0.0006

Data Index: 520455 (C4 (Web Text))

Max Activating Token Index: 446

Text #3

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0545. Min Act: -0.0006

Data Index: 874051 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0509. Min Act: -0.0006

Data Index: 857904 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0377. Min Act: -0.0006

Data Index: 1087152 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0457. Min Act: -0.0006

Data Index: 1269588 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0470. Min Act: -0.0006

Data Index: 242210 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0471. Min Act: -0.0006

Data Index: 1198711 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0436. Min Act: -0.0006

Data Index: 513707 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0440. Min Act: -0.0006

Data Index: 754284 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0457. Min Act: -0.0006

Data Index: 63342 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0436. Min Act: -0.0006

Data Index: 1312726 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0408. Min Act: -0.0006

Data Index: 514549 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0427. Min Act: -0.0006

Data Index: 974473 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0407. Min Act: -0.0006

Data Index: 461770 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0389. Min Act: -0.0006

Data Index: 728910 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0460. Min Act: -0.0006

Data Index: 636344 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0432. Min Act: -0.0006

Data Index: 698344 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0388. Min Act: -0.0006

Data Index: 1360697 (Python Code)

Max Activating Token Index: 613