Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 368 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.7019. Min Act: -0.0001

Data Index: 644206 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.7106. Min Act: -0.0001

Data Index: 21727 (C4 (Web Text))

Max Activating Token Index: 910

Text #2

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.7056. Min Act: -0.0001

Data Index: 1088518 (C4 (Web Text))

Max Activating Token Index: 567

Text #3

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.6303. Min Act: -0.0001

Data Index: 497741 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.6706. Min Act: -0.0001

Data Index: 225193 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.6812. Min Act: -0.0001

Data Index: 681900 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.6626. Min Act: -0.0001

Data Index: 189026 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.6656. Min Act: -0.0001

Data Index: 851277 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.6559. Min Act: -0.0001

Data Index: 641897 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.6284. Min Act: -0.0001

Data Index: 966972 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.5898. Min Act: -0.0001

Data Index: 457632 (C4 (Web Text))

Max Activating Token Index: 347

Text #11

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.6018. Min Act: -0.0001

Data Index: 231881 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.5765. Min Act: -0.0001

Data Index: 752877 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.6455. Min Act: -0.0001

Data Index: 590603 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.6261. Min Act: -0.0001

Data Index: 1005947 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.6145. Min Act: -0.0001

Data Index: 910398 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.5459. Min Act: -0.0001

Data Index: 941163 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.6363. Min Act: -0.0001

Data Index: 533035 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.6083. Min Act: -0.0001

Data Index: 946237 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.5619. Min Act: -0.0001

Data Index: 1051704 (C4 (Web Text))

Max Activating Token Index: 124