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

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

Neuron 852 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: 0.6526. Min Range: -0.6526

Max Act: 0.6526. Min Act: -0.0000

Data Index: 557291 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.6522. Min Act: -0.0000

Data Index: 494871 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.5883. Min Act: -0.0000

Data Index: 266973 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.5670. Min Act: -0.0000

Data Index: 134029 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.5475. Min Act: -0.0000

Data Index: 421695 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.5399. Min Act: -0.0000

Data Index: 510704 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.5757. Min Act: -0.0000

Data Index: 767280 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.5384. Min Act: -0.0000

Data Index: 467743 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.5348. Min Act: 0.0001

Data Index: 928320 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.5248. Min Act: -0.0000

Data Index: 732675 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.5010. Min Act: 0.0002

Data Index: 271093 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.4972. Min Act: -0.0000

Data Index: 25574 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.4857. Min Act: 0.0002

Data Index: 85764 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.4634. Min Act: -0.0000

Data Index: 141551 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.4418. Min Act: -0.0000

Data Index: 683258 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.4638. Min Act: -0.0000

Data Index: 1351856 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.4436. Min Act: -0.0000

Data Index: 738352 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.4464. Min Act: 0.0000

Data Index: 1327057 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.4362. Min Act: -0.0000

Data Index: 645866 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.4338. Min Act: -0.0000

Data Index: 1299604 (C4 (Web Text))

Max Activating Token Index: 277