Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1478 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0547. Min Act: -0.0001

Data Index: 485938 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0453. Min Act: -0.0001

Data Index: 343380 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0464. Min Act: -0.0001

Data Index: 612422 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0445. Min Act: -0.0001

Data Index: 613472 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0431. Min Act: -0.0001

Data Index: 1255087 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0426. Min Act: -0.0001

Data Index: 983660 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0419. Min Act: -0.0001

Data Index: 452787 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0404. Min Act: -0.0001

Data Index: 450482 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0428. Min Act: -0.0001

Data Index: 122345 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0418. Min Act: -0.0001

Data Index: 415815 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0407. Min Act: -0.0001

Data Index: 445277 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0393. Min Act: -0.0001

Data Index: 473281 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0410. Min Act: -0.0001

Data Index: 95855 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0383. Min Act: -0.0001

Data Index: 969717 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0391. Min Act: -0.0001

Data Index: 561635 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0398. Min Act: -0.0001

Data Index: 256377 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0373. Min Act: -0.0001

Data Index: 613614 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0390. Min Act: -0.0001

Data Index: 137489 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0412. Min Act: -0.0001

Data Index: 1348597 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0404. Min Act: -0.0001

Data Index: 518099 (C4 (Web Text))

Max Activating Token Index: 127