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

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

Neuron 408 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: 0.0613. Min Range: -0.0613

Max Act: 0.0613. Min Act: -0.0003

Data Index: 100091 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0576. Min Act: -0.0003

Data Index: 234209 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0549. Min Act: -0.0003

Data Index: 68598 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0531. Min Act: -0.0003

Data Index: 286117 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0526. Min Act: -0.0003

Data Index: 422041 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0532. Min Act: -0.0003

Data Index: 1141774 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0489. Min Act: -0.0003

Data Index: 773309 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0509. Min Act: -0.0003

Data Index: 1268609 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0490. Min Act: -0.0003

Data Index: 963718 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0438. Min Act: -0.0003

Data Index: 374946 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0496. Min Act: -0.0003

Data Index: 274825 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0437. Min Act: -0.0003

Data Index: 990947 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0452. Min Act: -0.0003

Data Index: 733867 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0416. Min Act: -0.0003

Data Index: 29306 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0442. Min Act: -0.0003

Data Index: 1181291 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0449. Min Act: -0.0003

Data Index: 102589 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0354. Min Act: -0.0003

Data Index: 1358718 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0477. Min Act: -0.0003

Data Index: 838386 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0458. Min Act: -0.0003

Data Index: 1022115 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0513. Min Act: -0.0003

Data Index: 586412 (C4 (Web Text))

Max Activating Token Index: 687