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

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

Neuron 135 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.9799. Min Act: -0.0003

Data Index: 25664 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.9726. Min Act: -0.0003

Data Index: 380843 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.9128. Min Act: -0.0003

Data Index: 882570 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.9446. Min Act: -0.0003

Data Index: 388434 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.9234. Min Act: -0.0003

Data Index: 652361 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.9435. Min Act: -0.0003

Data Index: 598639 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.9190. Min Act: -0.0003

Data Index: 790080 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8801. Min Act: -0.0003

Data Index: 1091545 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.7962. Min Act: -0.0003

Data Index: 1294760 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8942. Min Act: -0.0003

Data Index: 785087 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.9708. Min Act: -0.0003

Data Index: 492090 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8590. Min Act: -0.0003

Data Index: 1274237 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.7480. Min Act: -0.0003

Data Index: 615107 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8922. Min Act: -0.0003

Data Index: 276557 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8624. Min Act: -0.0003

Data Index: 885639 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8308. Min Act: -0.0003

Data Index: 873395 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8065. Min Act: -0.0003

Data Index: 1197066 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8776. Min Act: -0.0003

Data Index: 1289457 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.7724. Min Act: -0.0003

Data Index: 853541 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8210. Min Act: -0.0003

Data Index: 900716 (C4 (Web Text))

Max Activating Token Index: 804