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

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

Neuron 1684 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.5989. Min Act: -0.0001

Data Index: 1335967 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.6055. Min Act: -0.0001

Data Index: 541561 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.5761. Min Act: -0.0000

Data Index: 90018 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.5732. Min Act: -0.0001

Data Index: 707762 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.5390. Min Act: -0.0001

Data Index: 834405 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.5558. Min Act: -0.0001

Data Index: 599372 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.5525. Min Act: -0.0001

Data Index: 669817 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.5521. Min Act: -0.0001

Data Index: 854654 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.5033. Min Act: -0.0001

Data Index: 199727 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.5157. Min Act: -0.0001

Data Index: 300606 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.5304. Min Act: -0.0001

Data Index: 804350 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.5139. Min Act: -0.0001

Data Index: 171524 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.4946. Min Act: -0.0001

Data Index: 802490 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.4558. Min Act: -0.0001

Data Index: 1192193 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.4862. Min Act: -0.0001

Data Index: 1039142 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.4591. Min Act: -0.0001

Data Index: 131973 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.4582. Min Act: -0.0001

Data Index: 1104536 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.4566. Min Act: -0.0001

Data Index: 146142 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.4390. Min Act: -0.0001

Data Index: 1056656 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.4508. Min Act: -0.0001

Data Index: 565408 (C4 (Web Text))

Max Activating Token Index: 213