Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1670 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4698. Min Range: -1.4698

Max Act: 1.4545. Min Act: -0.0000

Data Index: 293037 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 1.4698. Min Range: -1.4698

Max Act: 1.4344. Min Act: -0.0000

Data Index: 943407 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 1.4698. Min Range: -1.4698

Max Act: 1.4698. Min Act: -0.0000

Data Index: 346229 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 1.4698. Min Range: -1.4698

Max Act: 1.3858. Min Act: -0.0000

Data Index: 175375 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 1.4698. Min Range: -1.4698

Max Act: 1.4056. Min Act: -0.0000

Data Index: 996004 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 1.4698. Min Range: -1.4698

Max Act: 1.4394. Min Act: -0.0000

Data Index: 614957 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 1.4698. Min Range: -1.4698

Max Act: 1.3415. Min Act: -0.0000

Data Index: 48768 (C4 (Web Text))

Max Activating Token Index: 572

Text #7

Max Range: 1.4698. Min Range: -1.4698

Max Act: 1.3752. Min Act: -0.0000

Data Index: 36814 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 1.4698. Min Range: -1.4698

Max Act: 1.3598. Min Act: -0.0000

Data Index: 767290 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 1.4698. Min Range: -1.4698

Max Act: 1.2436. Min Act: -0.0000

Data Index: 860356 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 1.4698. Min Range: -1.4698

Max Act: 1.2767. Min Act: -0.0000

Data Index: 1355680 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 1.4698. Min Range: -1.4698

Max Act: 1.3562. Min Act: -0.0000

Data Index: 436160 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 1.4698. Min Range: -1.4698

Max Act: 1.2102. Min Act: -0.0000

Data Index: 330382 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 1.4698. Min Range: -1.4698

Max Act: 1.2059. Min Act: -0.0000

Data Index: 1297623 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 1.4698. Min Range: -1.4698

Max Act: 1.2661. Min Act: -0.0000

Data Index: 108301 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 1.4698. Min Range: -1.4698

Max Act: 1.2414. Min Act: -0.0000

Data Index: 587116 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 1.4698. Min Range: -1.4698

Max Act: 1.1602. Min Act: -0.0000

Data Index: 119283 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 1.4698. Min Range: -1.4698

Max Act: 1.0802. Min Act: -0.0000

Data Index: 1017116 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 1.4698. Min Range: -1.4698

Max Act: 1.2179. Min Act: -0.0000

Data Index: 362023 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 1.4698. Min Range: -1.4698

Max Act: 1.0908. Min Act: -0.0000

Data Index: 737210 (C4 (Web Text))

Max Activating Token Index: 78