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

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

Neuron 2950 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0659. Min Act: -0.0002

Data Index: 300369 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0571. Min Act: -0.0002

Data Index: 80400 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0492. Min Act: -0.0002

Data Index: 835265 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1149085 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0407. Min Act: -0.0002

Data Index: 732539 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0401. Min Act: -0.0002

Data Index: 758186 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1192155 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0354. Min Act: -0.0002

Data Index: 969364 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0362. Min Act: -0.0002

Data Index: 614963 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0361. Min Act: -0.0002

Data Index: 207346 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1218326 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1358685 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0307. Min Act: -0.0002

Data Index: 205138 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0350. Min Act: -0.0002

Data Index: 259071 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0347. Min Act: -0.0002

Data Index: 119238 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0346. Min Act: -0.0002

Data Index: 103953 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0333. Min Act: -0.0002

Data Index: 201984 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0361. Min Act: -0.0002

Data Index: 315282 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1309685 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0337. Min Act: -0.0002

Data Index: 1299317 (C4 (Web Text))

Max Activating Token Index: 52