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

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

Neuron 17 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0516. Min Act: -0.0000

Data Index: 1580397 (Python Code)

Max Activating Token Index: 18

Text #1

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0498. Min Act: -0.0000

Data Index: 1388567 (Python Code)

Max Activating Token Index: 259

Text #2

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0484. Min Act: -0.0001

Data Index: 287865 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0515. Min Act: -0.0000

Data Index: 1400836 (Python Code)

Max Activating Token Index: 343

Text #4

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0469. Min Act: -0.0001

Data Index: 1248403 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0442. Min Act: -0.0001

Data Index: 210771 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0459. Min Act: -0.0001

Data Index: 722014 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0438. Min Act: -0.0001

Data Index: 1322474 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0404. Min Act: -0.0001

Data Index: 280667 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0416. Min Act: -0.0001

Data Index: 882999 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0479. Min Act: -0.0001

Data Index: 163594 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0424. Min Act: -0.0000

Data Index: 56818 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0431. Min Act: -0.0001

Data Index: 847236 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0467. Min Act: -0.0001

Data Index: 75557 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0426. Min Act: -0.0001

Data Index: 154933 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0427. Min Act: -0.0001

Data Index: 1357948 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0437. Min Act: -0.0001

Data Index: 982114 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0417. Min Act: -0.0001

Data Index: 187706 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0404. Min Act: -0.0000

Data Index: 1422200 (Python Code)

Max Activating Token Index: 323

Text #19

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0349. Min Act: -0.0001

Data Index: 639996 (C4 (Web Text))

Max Activating Token Index: 225