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

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

Neuron 2896 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.8765. Min Act: -0.0001

Data Index: 146547 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.9865. Min Act: -0.0001

Data Index: 1103987 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 1.0633. Min Range: -1.0633

Max Act: 1.0633. Min Act: -0.0001

Data Index: 1065524 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.9102. Min Act: -0.0001

Data Index: 619888 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.9236. Min Act: -0.0001

Data Index: 200854 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.8870. Min Act: -0.0001

Data Index: 1212489 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.8137. Min Act: -0.0001

Data Index: 1029489 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.8446. Min Act: -0.0001

Data Index: 178036 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.8623. Min Act: -0.0000

Data Index: 520738 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.8540. Min Act: -0.0001

Data Index: 1151118 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.7654. Min Act: -0.0001

Data Index: 942906 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.8244. Min Act: -0.0001

Data Index: 790399 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.8243. Min Act: -0.0000

Data Index: 860769 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.8006. Min Act: -0.0001

Data Index: 309962 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.9054. Min Act: -0.0001

Data Index: 667935 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.8191. Min Act: -0.0001

Data Index: 706648 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.8499. Min Act: -0.0001

Data Index: 953215 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.7677. Min Act: -0.0001

Data Index: 49032 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.8419. Min Act: -0.0001

Data Index: 737546 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.8800. Min Act: -0.0001

Data Index: 842793 (C4 (Web Text))

Max Activating Token Index: 200