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

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

Neuron 4498 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.3321. Min Act: -0.0000

Data Index: 344826 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.3360. Min Act: -0.0000

Data Index: 966376 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.2952. Min Act: -0.0000

Data Index: 735307 (C4 (Web Text))

Max Activating Token Index: 593

Text #3

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.2828. Min Act: -0.0000

Data Index: 1201558 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.2863. Min Act: -0.0000

Data Index: 827595 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.2601. Min Act: -0.0000

Data Index: 1093035 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.2700. Min Act: -0.0000

Data Index: 230459 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.2630. Min Act: -0.0000

Data Index: 1240120 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.2698. Min Act: -0.0000

Data Index: 994334 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.2504. Min Act: -0.0000

Data Index: 689228 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.2438. Min Act: -0.0000

Data Index: 63256 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.2504. Min Act: -0.0000

Data Index: 311693 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.2459. Min Act: -0.0000

Data Index: 695896 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.2367. Min Act: -0.0000

Data Index: 1148028 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.2419. Min Act: -0.0000

Data Index: 385388 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.2405. Min Act: -0.0000

Data Index: 1146723 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.2462. Min Act: -0.0000

Data Index: 850180 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.2223. Min Act: -0.0000

Data Index: 130356 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.2324. Min Act: -0.0000

Data Index: 165031 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 0.3360. Min Range: -0.3360

Max Act: 0.2309. Min Act: 0.0000

Data Index: 849665 (C4 (Web Text))

Max Activating Token Index: 502