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

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

Neuron 3491 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.8595. Min Act: -0.0000

Data Index: 936930 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.8552. Min Act: -0.0000

Data Index: 591616 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.7413. Min Act: -0.0000

Data Index: 1307185 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.7245. Min Act: -0.0000

Data Index: 372064 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.7467. Min Act: -0.0000

Data Index: 454226 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.7402. Min Act: -0.0000

Data Index: 908343 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.6985. Min Act: -0.0000

Data Index: 160222 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.6701. Min Act: -0.0000

Data Index: 1119478 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.6473. Min Act: -0.0000

Data Index: 841822 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.6840. Min Act: -0.0000

Data Index: 991403 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.7076. Min Act: -0.0000

Data Index: 1132403 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.6765. Min Act: -0.0000

Data Index: 948460 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.6707. Min Act: -0.0000

Data Index: 905493 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.6581. Min Act: -0.0000

Data Index: 539753 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.7031. Min Act: -0.0000

Data Index: 855493 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.6338. Min Act: -0.0000

Data Index: 61010 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.6069. Min Act: -0.0000

Data Index: 568546 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.6474. Min Act: -0.0000

Data Index: 1062174 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.6070. Min Act: -0.0000

Data Index: 918945 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.6423. Min Act: -0.0000

Data Index: 443166 (C4 (Web Text))

Max Activating Token Index: 908