Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1678 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0489. Min Act: -0.0002

Data Index: 101049 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0454. Min Act: -0.0001

Data Index: 943876 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0417. Min Act: -0.0001

Data Index: 673658 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0407. Min Act: -0.0002

Data Index: 376933 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0409. Min Act: -0.0002

Data Index: 1274572 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0399. Min Act: -0.0002

Data Index: 1271391 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0390. Min Act: -0.0001

Data Index: 142445 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0410. Min Act: -0.0002

Data Index: 327716 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0417. Min Act: -0.0001

Data Index: 751227 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0396. Min Act: -0.0001

Data Index: 774656 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0364. Min Act: -0.0002

Data Index: 286851 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0369. Min Act: -0.0001

Data Index: 138591 (C4 (Web Text))

Max Activating Token Index: 733

Text #12

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0378. Min Act: -0.0001

Data Index: 508954 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0381. Min Act: -0.0002

Data Index: 923152 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0340. Min Act: -0.0002

Data Index: 1304185 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0352. Min Act: -0.0002

Data Index: 360444 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0365. Min Act: -0.0002

Data Index: 1341520 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0367. Min Act: -0.0001

Data Index: 973156 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0367. Min Act: -0.0001

Data Index: 560183 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0335. Min Act: -0.0001

Data Index: 173847 (C4 (Web Text))

Max Activating Token Index: 632