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

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

Neuron 1490 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: 1.9233. Min Range: -1.9233

Max Act: 1.9233. Min Act: -0.0001

Data Index: 232645 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 1.9233. Min Range: -1.9233

Max Act: 1.8773. Min Act: -0.0001

Data Index: 1032057 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 1.9233. Min Range: -1.9233

Max Act: 1.8134. Min Act: -0.0001

Data Index: 1261335 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 1.9233. Min Range: -1.9233

Max Act: 1.6599. Min Act: -0.0001

Data Index: 583916 (C4 (Web Text))

Max Activating Token Index: 380

Text #4

Max Range: 1.9233. Min Range: -1.9233

Max Act: 1.7065. Min Act: -0.0001

Data Index: 1062605 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 1.9233. Min Range: -1.9233

Max Act: 1.4839. Min Act: -0.0001

Data Index: 459257 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 1.9233. Min Range: -1.9233

Max Act: 1.7481. Min Act: -0.0001

Data Index: 214423 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 1.9233. Min Range: -1.9233

Max Act: 1.7282. Min Act: -0.0001

Data Index: 1342009 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 1.9233. Min Range: -1.9233

Max Act: 1.7647. Min Act: -0.0001

Data Index: 246919 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 1.9233. Min Range: -1.9233

Max Act: 1.5715. Min Act: -0.0001

Data Index: 281715 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 1.9233. Min Range: -1.9233

Max Act: 1.6007. Min Act: -0.0001

Data Index: 1270510 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 1.9233. Min Range: -1.9233

Max Act: 1.3886. Min Act: -0.0001

Data Index: 850168 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 1.9233. Min Range: -1.9233

Max Act: 1.5666. Min Act: -0.0001

Data Index: 293192 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 1.9233. Min Range: -1.9233

Max Act: 1.5031. Min Act: -0.0001

Data Index: 1191029 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 1.9233. Min Range: -1.9233

Max Act: 1.6440. Min Act: -0.0001

Data Index: 975484 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 1.9233. Min Range: -1.9233

Max Act: 1.6993. Min Act: -0.0001

Data Index: 755628 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 1.9233. Min Range: -1.9233

Max Act: 1.5184. Min Act: -0.0001

Data Index: 27413 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 1.9233. Min Range: -1.9233

Max Act: 1.5996. Min Act: -0.0001

Data Index: 1310823 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 1.9233. Min Range: -1.9233

Max Act: 1.5007. Min Act: -0.0001

Data Index: 945006 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 1.9233. Min Range: -1.9233

Max Act: 1.5449. Min Act: -0.0001

Data Index: 113106 (C4 (Web Text))

Max Activating Token Index: 6