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

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

Neuron 756 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.9562. Min Act: -0.0001

Data Index: 109170 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.9979. Min Act: -0.0001

Data Index: 753526 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.8552. Min Act: -0.0001

Data Index: 188043 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.8739. Min Act: -0.0000

Data Index: 777102 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.8202. Min Act: -0.0001

Data Index: 87644 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.8764. Min Act: -0.0000

Data Index: 703639 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.7910. Min Act: -0.0000

Data Index: 1146685 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.8104. Min Act: -0.0000

Data Index: 797106 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.7737. Min Act: -0.0001

Data Index: 126027 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.7920. Min Act: -0.0000

Data Index: 19322 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.7867. Min Act: -0.0000

Data Index: 1109388 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.7588. Min Act: -0.0000

Data Index: 336776 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.7075. Min Act: -0.0000

Data Index: 380983 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.7459. Min Act: -0.0000

Data Index: 66744 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.7642. Min Act: -0.0000

Data Index: 383318 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.7550. Min Act: -0.0001

Data Index: 256905 (C4 (Web Text))

Max Activating Token Index: 964

Text #16

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.7753. Min Act: -0.0000

Data Index: 1261581 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.7385. Min Act: -0.0000

Data Index: 1249558 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.7379. Min Act: -0.0001

Data Index: 111249 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.7388. Min Act: -0.0000

Data Index: 972000 (C4 (Web Text))

Max Activating Token Index: 785