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

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

Neuron 2436 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.8116. Min Act: -0.0001

Data Index: 121959 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.7684. Min Act: -0.0001

Data Index: 23182 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.8628. Min Act: -0.0001

Data Index: 798146 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.7700. Min Act: -0.0001

Data Index: 693324 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.7850. Min Act: -0.0001

Data Index: 671534 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.7012. Min Act: -0.0001

Data Index: 1261230 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.7216. Min Act: -0.0001

Data Index: 696975 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.6460. Min Act: -0.0001

Data Index: 181410 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.6865. Min Act: -0.0001

Data Index: 157355 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.6498. Min Act: -0.0001

Data Index: 423888 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.6502. Min Act: -0.0001

Data Index: 177410 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.6116. Min Act: -0.0001

Data Index: 108742 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.6562. Min Act: -0.0001

Data Index: 101991 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.6537. Min Act: -0.0001

Data Index: 361602 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.6434. Min Act: -0.0001

Data Index: 1158944 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.6136. Min Act: -0.0001

Data Index: 644498 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.5679. Min Act: -0.0001

Data Index: 271732 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.6701. Min Act: -0.0001

Data Index: 947284 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.6202. Min Act: -0.0001

Data Index: 885839 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.5993. Min Act: -0.0001

Data Index: 241039 (C4 (Web Text))

Max Activating Token Index: 987