Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 520 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5866. Min Act: -0.0000

Data Index: 487203 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.6178. Min Act: -0.0000

Data Index: 1595031 (Python Code)

Max Activating Token Index: 99

Text #2

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.6386. Min Act: -0.0000

Data Index: 555394 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.6068. Min Act: -0.0000

Data Index: 703380 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.6086. Min Act: -0.0000

Data Index: 219159 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5876. Min Act: -0.0000

Data Index: 678585 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5928. Min Act: -0.0000

Data Index: 144507 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.6007. Min Act: -0.0000

Data Index: 412259 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.6135. Min Act: -0.0000

Data Index: 1619980 (Python Code)

Max Activating Token Index: 90

Text #9

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.6084. Min Act: -0.0000

Data Index: 1121131 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5559. Min Act: -0.0000

Data Index: 1181547 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5840. Min Act: -0.0000

Data Index: 1034853 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5621. Min Act: -0.0000

Data Index: 1256183 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.6175. Min Act: -0.0000

Data Index: 540246 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5616. Min Act: -0.0000

Data Index: 408034 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5955. Min Act: -0.0000

Data Index: 1005563 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5660. Min Act: -0.0000

Data Index: 251461 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5704. Min Act: -0.0000

Data Index: 1517920 (Python Code)

Max Activating Token Index: 23

Text #18

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5599. Min Act: -0.0000

Data Index: 12962 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5643. Min Act: -0.0000

Data Index: 1169160 (C4 (Web Text))

Max Activating Token Index: 263