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

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

Neuron 1513 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: 0.0462. Min Range: -0.0462

Max Act: 0.0453. Min Act: -0.0006

Data Index: 245526 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0461. Min Act: -0.0006

Data Index: 266351 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0420. Min Act: -0.0006

Data Index: 1124528 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0428. Min Act: -0.0006

Data Index: 596414 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0456. Min Act: -0.0006

Data Index: 504248 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0452. Min Act: -0.0006

Data Index: 234022 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0462. Min Act: -0.0006

Data Index: 102113 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0451. Min Act: -0.0006

Data Index: 576632 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0448. Min Act: -0.0006

Data Index: 1085229 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0438. Min Act: -0.0006

Data Index: 1213397 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0443. Min Act: -0.0006

Data Index: 410478 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0456. Min Act: -0.0006

Data Index: 328563 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0430. Min Act: -0.0006

Data Index: 21903 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0422. Min Act: -0.0006

Data Index: 1153022 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0420. Min Act: -0.0006

Data Index: 388766 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0428. Min Act: -0.0006

Data Index: 133276 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0428. Min Act: -0.0006

Data Index: 667569 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0433. Min Act: -0.0006

Data Index: 864407 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0425. Min Act: -0.0006

Data Index: 930129 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0398. Min Act: -0.0006

Data Index: 538812 (C4 (Web Text))

Max Activating Token Index: 300