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

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

Neuron 224 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8306. Min Range: -3.8306

Max Act: 3.8306. Min Act: -0.0001

Data Index: 118359 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 3.8306. Min Range: -3.8306

Max Act: 2.9535. Min Act: -0.0001

Data Index: 709243 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 3.8306. Min Range: -3.8306

Max Act: 3.1862. Min Act: -0.0001

Data Index: 703782 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 3.8306. Min Range: -3.8306

Max Act: 2.9876. Min Act: -0.0001

Data Index: 150411 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 3.8306. Min Range: -3.8306

Max Act: 2.9203. Min Act: -0.0001

Data Index: 740373 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 3.8306. Min Range: -3.8306

Max Act: 2.9661. Min Act: -0.0001

Data Index: 1030766 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 3.8306. Min Range: -3.8306

Max Act: 3.0593. Min Act: -0.0001

Data Index: 1067286 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 3.8306. Min Range: -3.8306

Max Act: 3.0365. Min Act: -0.0001

Data Index: 1132024 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 3.8306. Min Range: -3.8306

Max Act: 3.0252. Min Act: -0.0001

Data Index: 128806 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 3.8306. Min Range: -3.8306

Max Act: 2.8944. Min Act: -0.0001

Data Index: 71906 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 3.8306. Min Range: -3.8306

Max Act: 3.0345. Min Act: -0.0001

Data Index: 137986 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 3.8306. Min Range: -3.8306

Max Act: 2.8793. Min Act: -0.0001

Data Index: 849886 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 3.8306. Min Range: -3.8306

Max Act: 3.1610. Min Act: -0.0001

Data Index: 115871 (C4 (Web Text))

Max Activating Token Index: 740

Text #13

Max Range: 3.8306. Min Range: -3.8306

Max Act: 3.0010. Min Act: -0.0001

Data Index: 709135 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 3.8306. Min Range: -3.8306

Max Act: 2.9422. Min Act: -0.0001

Data Index: 1253738 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 3.8306. Min Range: -3.8306

Max Act: 3.0395. Min Act: -0.0001

Data Index: 742081 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 3.8306. Min Range: -3.8306

Max Act: 2.8664. Min Act: -0.0001

Data Index: 666524 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 3.8306. Min Range: -3.8306

Max Act: 2.8521. Min Act: -0.0001

Data Index: 1330625 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 3.8306. Min Range: -3.8306

Max Act: 2.9376. Min Act: -0.0001

Data Index: 1276753 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 3.8306. Min Range: -3.8306

Max Act: 3.0575. Min Act: -0.0001

Data Index: 215716 (C4 (Web Text))

Max Activating Token Index: 632