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

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

Neuron 3746 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: 0.7484. Min Range: -0.7484

Max Act: 0.7484. Min Act: -0.0001

Data Index: 1003421 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.7429. Min Act: -0.0001

Data Index: 27061 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.7460. Min Act: -0.0001

Data Index: 385081 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.7272. Min Act: -0.0001

Data Index: 1320062 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6853. Min Act: -0.0001

Data Index: 427622 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6717. Min Act: -0.0001

Data Index: 785 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6766. Min Act: -0.0001

Data Index: 586472 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6434. Min Act: -0.0001

Data Index: 1125351 (C4 (Web Text))

Max Activating Token Index: 510

Text #8

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6313. Min Act: -0.0001

Data Index: 2442 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6306. Min Act: -0.0001

Data Index: 545455 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6102. Min Act: -0.0001

Data Index: 484702 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6276. Min Act: -0.0001

Data Index: 799539 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6473. Min Act: -0.0001

Data Index: 1188148 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6261. Min Act: -0.0001

Data Index: 337697 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6036. Min Act: -0.0001

Data Index: 1042130 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.5970. Min Act: -0.0001

Data Index: 1334753 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6389. Min Act: -0.0001

Data Index: 130837 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6164. Min Act: -0.0001

Data Index: 1280640 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6140. Min Act: -0.0001

Data Index: 427435 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6125. Min Act: -0.0001

Data Index: 138063 (C4 (Web Text))

Max Activating Token Index: 952