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

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

Neuron 3709 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0529. Min Act: -0.0000

Data Index: 558393 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0488. Min Act: -0.0000

Data Index: 1425724 (Python Code)

Max Activating Token Index: 514

Text #2

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0506. Min Act: -0.0000

Data Index: 596689 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0487. Min Act: -0.0000

Data Index: 1030959 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0466. Min Act: -0.0000

Data Index: 125151 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0469. Min Act: -0.0000

Data Index: 1166353 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0482. Min Act: -0.0000

Data Index: 867415 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0488. Min Act: -0.0000

Data Index: 555936 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0486. Min Act: -0.0000

Data Index: 385272 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0438. Min Act: -0.0000

Data Index: 1230729 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0451. Min Act: -0.0000

Data Index: 118099 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0423. Min Act: -0.0000

Data Index: 715221 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0424. Min Act: -0.0000

Data Index: 355651 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0435. Min Act: -0.0000

Data Index: 1400055 (Python Code)

Max Activating Token Index: 231

Text #14

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0468. Min Act: -0.0000

Data Index: 238790 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0416. Min Act: -0.0000

Data Index: 304658 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0423. Min Act: -0.0000

Data Index: 243340 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0417. Min Act: -0.0000

Data Index: 524695 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0430. Min Act: -0.0000

Data Index: 180029 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0425. Min Act: -0.0000

Data Index: 759244 (C4 (Web Text))

Max Activating Token Index: 729