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

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

Neuron 2424 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0082. Min Range: -1.0082

Max Act: 1.0082. Min Act: -0.0000

Data Index: 364233 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 1.0082. Min Range: -1.0082

Max Act: 0.8160. Min Act: -0.0000

Data Index: 1349512 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 1.0082. Min Range: -1.0082

Max Act: 0.8956. Min Act: -0.0000

Data Index: 1216072 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 1.0082. Min Range: -1.0082

Max Act: 0.6110. Min Act: -0.0000

Data Index: 314880 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 1.0082. Min Range: -1.0082

Max Act: 0.6125. Min Act: -0.0000

Data Index: 80573 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 1.0082. Min Range: -1.0082

Max Act: 0.5983. Min Act: 0.0000

Data Index: 543164 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 1.0082. Min Range: -1.0082

Max Act: 0.6059. Min Act: -0.0000

Data Index: 1681 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 1.0082. Min Range: -1.0082

Max Act: 0.5586. Min Act: -0.0000

Data Index: 83999 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 1.0082. Min Range: -1.0082

Max Act: 0.5372. Min Act: -0.0000

Data Index: 185663 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 1.0082. Min Range: -1.0082

Max Act: 0.4923. Min Act: -0.0000

Data Index: 217703 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 1.0082. Min Range: -1.0082

Max Act: 0.5156. Min Act: -0.0000

Data Index: 735910 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 1.0082. Min Range: -1.0082

Max Act: 0.5022. Min Act: -0.0000

Data Index: 1323987 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 1.0082. Min Range: -1.0082

Max Act: 0.4934. Min Act: -0.0000

Data Index: 690729 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 1.0082. Min Range: -1.0082

Max Act: 0.4887. Min Act: -0.0000

Data Index: 427902 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 1.0082. Min Range: -1.0082

Max Act: 0.4959. Min Act: -0.0000

Data Index: 1156769 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 1.0082. Min Range: -1.0082

Max Act: 0.4409. Min Act: -0.0000

Data Index: 469350 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 1.0082. Min Range: -1.0082

Max Act: 0.4495. Min Act: -0.0000

Data Index: 926310 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 1.0082. Min Range: -1.0082

Max Act: 0.4263. Min Act: -0.0000

Data Index: 440343 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 1.0082. Min Range: -1.0082

Max Act: 0.4519. Min Act: -0.0000

Data Index: 1332508 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 1.0082. Min Range: -1.0082

Max Act: 0.4050. Min Act: -0.0000

Data Index: 195221 (C4 (Web Text))

Max Activating Token Index: 316