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

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

Neuron 328 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9655. Min Range: -0.9655

Max Act: 0.9655. Min Act: -0.0000

Data Index: 212999 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 0.9655. Min Range: -0.9655

Max Act: 0.8934. Min Act: -0.0000

Data Index: 1353085 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 0.9655. Min Range: -0.9655

Max Act: 0.8160. Min Act: -0.0000

Data Index: 440600 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 0.9655. Min Range: -0.9655

Max Act: 0.8215. Min Act: -0.0000

Data Index: 531265 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 0.9655. Min Range: -0.9655

Max Act: 0.7847. Min Act: -0.0000

Data Index: 101691 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 0.9655. Min Range: -0.9655

Max Act: 0.7765. Min Act: -0.0000

Data Index: 1342747 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 0.9655. Min Range: -0.9655

Max Act: 0.8134. Min Act: -0.0000

Data Index: 96684 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.9655. Min Range: -0.9655

Max Act: 0.7725. Min Act: -0.0000

Data Index: 900104 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 0.9655. Min Range: -0.9655

Max Act: 0.7372. Min Act: -0.0000

Data Index: 969668 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 0.9655. Min Range: -0.9655

Max Act: 0.7362. Min Act: -0.0000

Data Index: 864327 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 0.9655. Min Range: -0.9655

Max Act: 0.7578. Min Act: -0.0000

Data Index: 182968 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 0.9655. Min Range: -0.9655

Max Act: 0.7522. Min Act: -0.0000

Data Index: 470362 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 0.9655. Min Range: -0.9655

Max Act: 0.7413. Min Act: -0.0000

Data Index: 552085 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 0.9655. Min Range: -0.9655

Max Act: 0.7350. Min Act: -0.0000

Data Index: 313694 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.9655. Min Range: -0.9655

Max Act: 0.7312. Min Act: -0.0000

Data Index: 611727 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 0.9655. Min Range: -0.9655

Max Act: 0.7078. Min Act: -0.0000

Data Index: 1031539 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 0.9655. Min Range: -0.9655

Max Act: 0.7281. Min Act: -0.0000

Data Index: 1232287 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 0.9655. Min Range: -0.9655

Max Act: 0.7301. Min Act: -0.0000

Data Index: 1216884 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 0.9655. Min Range: -0.9655

Max Act: 0.7228. Min Act: -0.0000

Data Index: 1037260 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 0.9655. Min Range: -0.9655

Max Act: 0.7366. Min Act: -0.0000

Data Index: 1106770 (C4 (Web Text))

Max Activating Token Index: 113