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

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

Neuron 2217 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.5784. Min Act: -0.0004

Data Index: 996573 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.5671. Min Act: -0.0004

Data Index: 25373 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.5671. Min Act: -0.0004

Data Index: 1105209 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.5671. Min Act: -0.0004

Data Index: 595569 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.5139. Min Act: -0.0004

Data Index: 471983 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.5152. Min Act: -0.0004

Data Index: 239772 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.5325. Min Act: -0.0004

Data Index: 1209212 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.5473. Min Act: -0.0004

Data Index: 151507 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.4993. Min Act: -0.0004

Data Index: 229536 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.5321. Min Act: -0.0004

Data Index: 1108001 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.5131. Min Act: -0.0004

Data Index: 449785 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.4642. Min Act: -0.0004

Data Index: 297173 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.4740. Min Act: -0.0004

Data Index: 904244 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.4765. Min Act: -0.0004

Data Index: 1296719 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.4429. Min Act: -0.0004

Data Index: 1170003 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.4875. Min Act: -0.0004

Data Index: 29789 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.4558. Min Act: -0.0004

Data Index: 1157711 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.5366. Min Act: -0.0004

Data Index: 1254018 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.4810. Min Act: -0.0004

Data Index: 648762 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.5109. Min Act: -0.0004

Data Index: 1009665 (C4 (Web Text))

Max Activating Token Index: 986