Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1326 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.3476. Min Act: -0.0001

Data Index: 136420 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.3245. Min Act: -0.0001

Data Index: 1165902 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2878. Min Act: -0.0001

Data Index: 264020 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2692. Min Act: -0.0001

Data Index: 638447 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2725. Min Act: -0.0001

Data Index: 599170 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2914. Min Act: -0.0000

Data Index: 123017 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2814. Min Act: -0.0001

Data Index: 160735 (C4 (Web Text))

Max Activating Token Index: 924

Text #7

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2679. Min Act: -0.0001

Data Index: 1159982 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2792. Min Act: -0.0001

Data Index: 893220 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2728. Min Act: -0.0000

Data Index: 86567 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2614. Min Act: -0.0000

Data Index: 1253761 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2556. Min Act: -0.0000

Data Index: 1153496 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2554. Min Act: -0.0000

Data Index: 662102 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2524. Min Act: -0.0001

Data Index: 35023 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2432. Min Act: -0.0000

Data Index: 713780 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2565. Min Act: -0.0001

Data Index: 374110 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2385. Min Act: -0.0000

Data Index: 1094109 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2698. Min Act: -0.0001

Data Index: 509715 (C4 (Web Text))

Max Activating Token Index: 554

Text #18

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2333. Min Act: -0.0001

Data Index: 1309120 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2377. Min Act: -0.0000

Data Index: 995041 (C4 (Web Text))

Max Activating Token Index: 390