Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 391 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0470. Min Act: -0.0000

Data Index: 1668317 (The Pile)

Max Activating Token Index: 978

Text #1

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0495. Min Act: -0.0000

Data Index: 239270 (The Pile)

Max Activating Token Index: 1007

Text #2

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0496. Min Act: -0.0000

Data Index: 282526 (The Pile)

Max Activating Token Index: 866

Text #3

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0487. Min Act: -0.0000

Data Index: 127185 (The Pile)

Max Activating Token Index: 1016

Text #4

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0436. Min Act: -0.0000

Data Index: 421541 (The Pile)

Max Activating Token Index: 152

Text #5

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0459. Min Act: -0.0000

Data Index: 1889191 (The Pile)

Max Activating Token Index: 605

Text #6

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0431. Min Act: -0.0000

Data Index: 680024 (The Pile)

Max Activating Token Index: 982

Text #7

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0438. Min Act: -0.0000

Data Index: 1141990 (The Pile)

Max Activating Token Index: 947

Text #8

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0407. Min Act: -0.0000

Data Index: 1222088 (The Pile)

Max Activating Token Index: 39

Text #9

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0398. Min Act: -0.0000

Data Index: 304844 (The Pile)

Max Activating Token Index: 573

Text #10

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0409. Min Act: -0.0000

Data Index: 288010 (The Pile)

Max Activating Token Index: 1005

Text #11

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0377. Min Act: -0.0000

Data Index: 1456176 (The Pile)

Max Activating Token Index: 268

Text #12

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0391. Min Act: -0.0000

Data Index: 635013 (The Pile)

Max Activating Token Index: 240

Text #13

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0377. Min Act: -0.0000

Data Index: 440264 (The Pile)

Max Activating Token Index: 156

Text #14

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0374. Min Act: -0.0000

Data Index: 1182459 (The Pile)

Max Activating Token Index: 437

Text #15

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0404. Min Act: -0.0000

Data Index: 1765566 (The Pile)

Max Activating Token Index: 802

Text #16

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0351. Min Act: -0.0000

Data Index: 1198962 (The Pile)

Max Activating Token Index: 366

Text #17

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0377. Min Act: -0.0000

Data Index: 1319579 (The Pile)

Max Activating Token Index: 65

Text #18

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0361. Min Act: -0.0000

Data Index: 981252 (The Pile)

Max Activating Token Index: 880

Text #19

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0382. Min Act: -0.0000

Data Index: 1821251 (The Pile)

Max Activating Token Index: 676