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

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

Neuron 1092 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1352. Min Range: -1.1352

Max Act: 1.1352. Min Act: -0.0001

Data Index: 606391 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 1.1352. Min Range: -1.1352

Max Act: 1.0000. Min Act: -0.0001

Data Index: 98665 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.8631. Min Act: -0.0001

Data Index: 1319201 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.7579. Min Act: -0.0001

Data Index: 1290055 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.8311. Min Act: -0.0001

Data Index: 485797 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.8439. Min Act: -0.0001

Data Index: 651934 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.8872. Min Act: -0.0001

Data Index: 472125 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.8099. Min Act: -0.0001

Data Index: 467636 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.8125. Min Act: -0.0001

Data Index: 1034721 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.7650. Min Act: -0.0001

Data Index: 1084042 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.6182. Min Act: -0.0001

Data Index: 1194264 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.5618. Min Act: -0.0001

Data Index: 526617 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.6456. Min Act: -0.0001

Data Index: 677996 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.6699. Min Act: -0.0001

Data Index: 832659 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.7032. Min Act: -0.0001

Data Index: 934806 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.7599. Min Act: -0.0001

Data Index: 264668 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.6939. Min Act: -0.0001

Data Index: 1434291 (Python Code)

Max Activating Token Index: 363

Text #17

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.8211. Min Act: -0.0001

Data Index: 506120 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.5828. Min Act: -0.0001

Data Index: 1236402 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.6423. Min Act: -0.0001

Data Index: 1135892 (C4 (Web Text))

Max Activating Token Index: 743