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

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

Neuron 3909 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7121. Min Range: -0.7121

Max Act: 0.7121. Min Act: -0.0001

Data Index: 379958 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 0.7121. Min Range: -0.7121

Max Act: 0.6240. Min Act: -0.0001

Data Index: 235324 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 0.7121. Min Range: -0.7121

Max Act: 0.6105. Min Act: -0.0001

Data Index: 1316333 (C4 (Web Text))

Max Activating Token Index: 439

Text #3

Max Range: 0.7121. Min Range: -0.7121

Max Act: 0.5950. Min Act: -0.0001

Data Index: 1003391 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 0.7121. Min Range: -0.7121

Max Act: 0.4890. Min Act: -0.0001

Data Index: 631138 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 0.7121. Min Range: -0.7121

Max Act: 0.5580. Min Act: -0.0001

Data Index: 1340102 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 0.7121. Min Range: -0.7121

Max Act: 0.5069. Min Act: -0.0001

Data Index: 411486 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 0.7121. Min Range: -0.7121

Max Act: 0.5202. Min Act: -0.0001

Data Index: 44429 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 0.7121. Min Range: -0.7121

Max Act: 0.4991. Min Act: -0.0001

Data Index: 76384 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 0.7121. Min Range: -0.7121

Max Act: 0.5124. Min Act: -0.0001

Data Index: 1027701 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.7121. Min Range: -0.7121

Max Act: 0.4407. Min Act: -0.0001

Data Index: 1001754 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.7121. Min Range: -0.7121

Max Act: 0.5083. Min Act: -0.0001

Data Index: 1176718 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 0.7121. Min Range: -0.7121

Max Act: 0.5363. Min Act: -0.0001

Data Index: 865266 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 0.7121. Min Range: -0.7121

Max Act: 0.4641. Min Act: -0.0001

Data Index: 1174293 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 0.7121. Min Range: -0.7121

Max Act: 0.4625. Min Act: -0.0001

Data Index: 135544 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 0.7121. Min Range: -0.7121

Max Act: 0.5073. Min Act: -0.0001

Data Index: 171871 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 0.7121. Min Range: -0.7121

Max Act: 0.4751. Min Act: -0.0001

Data Index: 976407 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 0.7121. Min Range: -0.7121

Max Act: 0.4862. Min Act: -0.0001

Data Index: 1053373 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 0.7121. Min Range: -0.7121

Max Act: 0.4722. Min Act: -0.0001

Data Index: 793132 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 0.7121. Min Range: -0.7121

Max Act: 0.5018. Min Act: -0.0001

Data Index: 963971 (C4 (Web Text))

Max Activating Token Index: 785