Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1328 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0407. Min Act: -0.0003

Data Index: 769329 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0406. Min Act: -0.0003

Data Index: 587369 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0362. Min Act: -0.0003

Data Index: 861176 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0362. Min Act: -0.0003

Data Index: 247241 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0353. Min Act: -0.0003

Data Index: 1093554 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0353. Min Act: -0.0003

Data Index: 589789 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0354. Min Act: -0.0003

Data Index: 882800 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0355. Min Act: -0.0002

Data Index: 101998 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0355. Min Act: -0.0003

Data Index: 821276 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0355. Min Act: -0.0003

Data Index: 1182830 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0348. Min Act: -0.0003

Data Index: 492662 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0342. Min Act: -0.0003

Data Index: 715317 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0346. Min Act: -0.0003

Data Index: 722304 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0343. Min Act: -0.0003

Data Index: 256978 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0350. Min Act: -0.0004

Data Index: 1116935 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0349. Min Act: -0.0004

Data Index: 438527 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0338. Min Act: -0.0003

Data Index: 710284 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0357. Min Act: -0.0003

Data Index: 1272160 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0336. Min Act: -0.0003

Data Index: 46901 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0328. Min Act: -0.0003

Data Index: 1026601 (C4 (Web Text))

Max Activating Token Index: 319