Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 925 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2845. Min Range: -2.2845

Max Act: 2.2845. Min Act: -0.0000

Data Index: 658423 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 2.2845. Min Range: -2.2845

Max Act: 1.5758. Min Act: -0.0000

Data Index: 361868 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 2.2845. Min Range: -2.2845

Max Act: 1.6004. Min Act: -0.0000

Data Index: 472154 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 2.2845. Min Range: -2.2845

Max Act: 1.3064. Min Act: -0.0000

Data Index: 1230130 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 2.2845. Min Range: -2.2845

Max Act: 1.3161. Min Act: -0.0000

Data Index: 63391 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 2.2845. Min Range: -2.2845

Max Act: 1.3125. Min Act: -0.0000

Data Index: 1123154 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 2.2845. Min Range: -2.2845

Max Act: 1.2233. Min Act: -0.0000

Data Index: 1026541 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 2.2845. Min Range: -2.2845

Max Act: 1.2089. Min Act: -0.0000

Data Index: 371381 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 2.2845. Min Range: -2.2845

Max Act: 1.1180. Min Act: -0.0000

Data Index: 628229 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 2.2845. Min Range: -2.2845

Max Act: 1.1385. Min Act: -0.0000

Data Index: 1150205 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 2.2845. Min Range: -2.2845

Max Act: 1.1437. Min Act: -0.0000

Data Index: 767426 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 2.2845. Min Range: -2.2845

Max Act: 1.1743. Min Act: -0.0000

Data Index: 454620 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 2.2845. Min Range: -2.2845

Max Act: 1.0665. Min Act: -0.0000

Data Index: 266282 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 2.2845. Min Range: -2.2845

Max Act: 1.1369. Min Act: -0.0000

Data Index: 893445 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 2.2845. Min Range: -2.2845

Max Act: 1.0865. Min Act: -0.0000

Data Index: 1317780 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 2.2845. Min Range: -2.2845

Max Act: 1.1093. Min Act: -0.0000

Data Index: 141007 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 2.2845. Min Range: -2.2845

Max Act: 1.0716. Min Act: -0.0000

Data Index: 320897 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 2.2845. Min Range: -2.2845

Max Act: 1.0659. Min Act: -0.0000

Data Index: 1308585 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 2.2845. Min Range: -2.2845

Max Act: 1.0026. Min Act: -0.0000

Data Index: 850065 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 2.2845. Min Range: -2.2845

Max Act: 1.0524. Min Act: -0.0000

Data Index: 363156 (C4 (Web Text))

Max Activating Token Index: 363