Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 253 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 3.4109. Min Range: -3.4109

Max Act: 3.4109. Min Act: -0.0001

Data Index: 638708 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 3.4109. Min Range: -3.4109

Max Act: 2.2454. Min Act: -0.0001

Data Index: 1268754 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 3.4109. Min Range: -3.4109

Max Act: 2.2403. Min Act: -0.0001

Data Index: 1218475 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 3.4109. Min Range: -3.4109

Max Act: 2.3040. Min Act: -0.0001

Data Index: 659195 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 3.4109. Min Range: -3.4109

Max Act: 2.1630. Min Act: -0.0001

Data Index: 1351309 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 3.4109. Min Range: -3.4109

Max Act: 2.1701. Min Act: -0.0001

Data Index: 714342 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 3.4109. Min Range: -3.4109

Max Act: 2.0283. Min Act: -0.0001

Data Index: 343524 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 3.4109. Min Range: -3.4109

Max Act: 2.0876. Min Act: -0.0001

Data Index: 1038153 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 3.4109. Min Range: -3.4109

Max Act: 2.0807. Min Act: -0.0001

Data Index: 840733 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 3.4109. Min Range: -3.4109

Max Act: 1.8424. Min Act: -0.0001

Data Index: 990909 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 3.4109. Min Range: -3.4109

Max Act: 1.8729. Min Act: -0.0001

Data Index: 617697 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 3.4109. Min Range: -3.4109

Max Act: 1.8274. Min Act: -0.0001

Data Index: 109766 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 3.4109. Min Range: -3.4109

Max Act: 1.8716. Min Act: -0.0001

Data Index: 808788 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 3.4109. Min Range: -3.4109

Max Act: 1.8492. Min Act: -0.0001

Data Index: 1355219 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 3.4109. Min Range: -3.4109

Max Act: 1.6965. Min Act: -0.0001

Data Index: 529518 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 3.4109. Min Range: -3.4109

Max Act: 1.7115. Min Act: -0.0001

Data Index: 1135839 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 3.4109. Min Range: -3.4109

Max Act: 1.6152. Min Act: -0.0001

Data Index: 60402 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 3.4109. Min Range: -3.4109

Max Act: 1.6569. Min Act: -0.0001

Data Index: 1118411 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 3.4109. Min Range: -3.4109

Max Act: 1.6497. Min Act: -0.0001

Data Index: 454390 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 3.4109. Min Range: -3.4109

Max Act: 1.7538. Min Act: -0.0001

Data Index: 265505 (C4 (Web Text))

Max Activating Token Index: 26