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

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

Neuron 3091 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2339. Min Act: -0.0001

Data Index: 1271467 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2870. Min Act: -0.0001

Data Index: 255056 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2675. Min Act: -0.0001

Data Index: 195260 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2672. Min Act: -0.0001

Data Index: 291777 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2597. Min Act: -0.0001

Data Index: 587612 (C4 (Web Text))

Max Activating Token Index: 425

Text #5

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2559. Min Act: -0.0001

Data Index: 97360 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2192. Min Act: -0.0001

Data Index: 429052 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2403. Min Act: -0.0001

Data Index: 510362 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2287. Min Act: -0.0001

Data Index: 840325 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2475. Min Act: -0.0001

Data Index: 1085086 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2518. Min Act: -0.0001

Data Index: 1115300 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2399. Min Act: -0.0001

Data Index: 15714 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2403. Min Act: -0.0001

Data Index: 800455 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2473. Min Act: -0.0001

Data Index: 548422 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2366. Min Act: -0.0001

Data Index: 1247437 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2474. Min Act: -0.0001

Data Index: 428089 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2361. Min Act: -0.0001

Data Index: 754603 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2222. Min Act: -0.0001

Data Index: 314863 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2304. Min Act: -0.0001

Data Index: 332760 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2212. Min Act: -0.0001

Data Index: 994902 (C4 (Web Text))

Max Activating Token Index: 700