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

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

Neuron 2887 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: 0.8581. Min Range: -0.8581

Max Act: 0.8581. Min Act: -0.0001

Data Index: 713997 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.8366. Min Act: -0.0001

Data Index: 1322879 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.8153. Min Act: -0.0001

Data Index: 326068 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7583. Min Act: -0.0001

Data Index: 362731 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7793. Min Act: -0.0001

Data Index: 625066 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7994. Min Act: -0.0001

Data Index: 1331544 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7317. Min Act: -0.0001

Data Index: 1639444 (Python Code)

Max Activating Token Index: 191

Text #7

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.6828. Min Act: -0.0001

Data Index: 1055306 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.6635. Min Act: -0.0001

Data Index: 1084172 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.6891. Min Act: -0.0001

Data Index: 444999 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.6844. Min Act: -0.0001

Data Index: 682283 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.6491. Min Act: -0.0001

Data Index: 119855 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.6369. Min Act: -0.0001

Data Index: 495270 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.6143. Min Act: -0.0001

Data Index: 1317062 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.6838. Min Act: -0.0001

Data Index: 673539 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.6645. Min Act: -0.0001

Data Index: 746309 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.6553. Min Act: -0.0001

Data Index: 257810 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.6298. Min Act: -0.0001

Data Index: 896954 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.6116. Min Act: -0.0001

Data Index: 490025 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.5673. Min Act: -0.0001

Data Index: 1084964 (C4 (Web Text))

Max Activating Token Index: 949