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

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

Neuron 142 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: 3.1435. Min Range: -3.1435

Max Act: 3.1435. Min Act: -0.0000

Data Index: 938759 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 3.1435. Min Range: -3.1435

Max Act: 3.0566. Min Act: -0.0000

Data Index: 645498 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 3.1435. Min Range: -3.1435

Max Act: 3.0892. Min Act: -0.0000

Data Index: 291578 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 3.1435. Min Range: -3.1435

Max Act: 2.9507. Min Act: -0.0000

Data Index: 707029 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 3.1435. Min Range: -3.1435

Max Act: 2.9305. Min Act: -0.0000

Data Index: 591788 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 3.1435. Min Range: -3.1435

Max Act: 2.6886. Min Act: -0.0000

Data Index: 111580 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 3.1435. Min Range: -3.1435

Max Act: 2.7147. Min Act: -0.0000

Data Index: 389670 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 3.1435. Min Range: -3.1435

Max Act: 2.8328. Min Act: -0.0000

Data Index: 1026238 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 3.1435. Min Range: -3.1435

Max Act: 2.8044. Min Act: -0.0000

Data Index: 17597 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 3.1435. Min Range: -3.1435

Max Act: 2.6370. Min Act: -0.0000

Data Index: 346557 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 3.1435. Min Range: -3.1435

Max Act: 2.7036. Min Act: -0.0000

Data Index: 1241157 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 3.1435. Min Range: -3.1435

Max Act: 2.6146. Min Act: -0.0000

Data Index: 68510 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 3.1435. Min Range: -3.1435

Max Act: 2.5868. Min Act: -0.0000

Data Index: 927205 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 3.1435. Min Range: -3.1435

Max Act: 2.5828. Min Act: -0.0000

Data Index: 197963 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 3.1435. Min Range: -3.1435

Max Act: 2.4477. Min Act: -0.0000

Data Index: 980002 (C4 (Web Text))

Max Activating Token Index: 855

Text #15

Max Range: 3.1435. Min Range: -3.1435

Max Act: 2.4450. Min Act: -0.0000

Data Index: 486336 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 3.1435. Min Range: -3.1435

Max Act: 2.5588. Min Act: -0.0000

Data Index: 683219 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 3.1435. Min Range: -3.1435

Max Act: 2.2986. Min Act: -0.0000

Data Index: 1120361 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 3.1435. Min Range: -3.1435

Max Act: 2.6679. Min Act: -0.0000

Data Index: 568767 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 3.1435. Min Range: -3.1435

Max Act: 2.5254. Min Act: -0.0000

Data Index: 1254194 (C4 (Web Text))

Max Activating Token Index: 1010