Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3320 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0451. Min Range: -1.0451

Max Act: 1.0451. Min Act: -0.0001

Data Index: 650273 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.8324. Min Act: -0.0001

Data Index: 255620 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.8355. Min Act: -0.0001

Data Index: 978620 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.8366. Min Act: -0.0001

Data Index: 125447 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.8265. Min Act: -0.0001

Data Index: 1010433 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.8308. Min Act: -0.0001

Data Index: 809076 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.7905. Min Act: -0.0001

Data Index: 435901 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.7846. Min Act: -0.0001

Data Index: 1212087 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.7278. Min Act: -0.0001

Data Index: 949251 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.7666. Min Act: -0.0001

Data Index: 1351054 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.7595. Min Act: -0.0001

Data Index: 1085513 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.7800. Min Act: -0.0001

Data Index: 481356 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.7066. Min Act: -0.0001

Data Index: 1082890 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.7033. Min Act: -0.0001

Data Index: 378077 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.6864. Min Act: -0.0001

Data Index: 1183021 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.6777. Min Act: -0.0001

Data Index: 907580 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.7415. Min Act: -0.0001

Data Index: 909637 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.7392. Min Act: -0.0001

Data Index: 507710 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.7156. Min Act: -0.0001

Data Index: 468026 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.6962. Min Act: -0.0001

Data Index: 461708 (C4 (Web Text))

Max Activating Token Index: 634