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

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

Neuron 1943 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: 0.0543. Min Range: -0.0543

Max Act: 0.0539. Min Act: -0.0006

Data Index: 109297 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0543. Min Act: -0.0005

Data Index: 880109 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0529. Min Act: -0.0006

Data Index: 980668 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0500. Min Act: -0.0006

Data Index: 414955 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0514. Min Act: -0.0006

Data Index: 436866 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0490. Min Act: -0.0006

Data Index: 157801 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0488. Min Act: -0.0006

Data Index: 126953 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0484. Min Act: -0.0006

Data Index: 1337765 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0503. Min Act: -0.0006

Data Index: 533673 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0491. Min Act: -0.0006

Data Index: 736342 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0491. Min Act: -0.0006

Data Index: 138271 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0500. Min Act: -0.0006

Data Index: 1271603 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0496. Min Act: -0.0006

Data Index: 87770 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0485. Min Act: -0.0006

Data Index: 314541 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0474. Min Act: -0.0006

Data Index: 1149522 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0483. Min Act: -0.0006

Data Index: 936477 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0482. Min Act: -0.0006

Data Index: 461560 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0483. Min Act: -0.0006

Data Index: 274089 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0482. Min Act: -0.0006

Data Index: 797035 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0473. Min Act: -0.0006

Data Index: 603633 (C4 (Web Text))

Max Activating Token Index: 136