Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2037 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0429. Min Act: -0.0006

Data Index: 777081 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0429. Min Act: -0.0005

Data Index: 1330875 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0426. Min Act: -0.0005

Data Index: 1206349 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0400. Min Act: -0.0006

Data Index: 502327 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0409. Min Act: -0.0006

Data Index: 114254 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0402. Min Act: -0.0006

Data Index: 960170 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0398. Min Act: -0.0006

Data Index: 1330415 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0385. Min Act: -0.0006

Data Index: 751738 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0400. Min Act: -0.0006

Data Index: 289846 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0383. Min Act: -0.0006

Data Index: 480025 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0383. Min Act: -0.0006

Data Index: 260767 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0390. Min Act: -0.0006

Data Index: 333250 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0414. Min Act: -0.0006

Data Index: 1532238 (Python Code)

Max Activating Token Index: 252

Text #13

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0412. Min Act: -0.0006

Data Index: 3062 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0407. Min Act: -0.0006

Data Index: 487702 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0350. Min Act: -0.0006

Data Index: 984304 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0370. Min Act: -0.0006

Data Index: 1112522 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0391. Min Act: -0.0006

Data Index: 1346689 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0388. Min Act: -0.0005

Data Index: 1223599 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0413. Min Act: -0.0005

Data Index: 929972 (C4 (Web Text))

Max Activating Token Index: 489