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

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

Neuron 1078 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4846. Min Range: -3.4846

Max Act: 3.4846. Min Act: -0.0000

Data Index: 775731 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 3.4846. Min Range: -3.4846

Max Act: 3.1652. Min Act: -0.0000

Data Index: 533875 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 3.4846. Min Range: -3.4846

Max Act: 3.2176. Min Act: -0.0000

Data Index: 1125726 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 3.4846. Min Range: -3.4846

Max Act: 2.8885. Min Act: -0.0000

Data Index: 114256 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 3.4846. Min Range: -3.4846

Max Act: 3.0494. Min Act: -0.0000

Data Index: 471694 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 3.4846. Min Range: -3.4846

Max Act: 3.1121. Min Act: -0.0000

Data Index: 780651 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 3.4846. Min Range: -3.4846

Max Act: 3.0699. Min Act: -0.0000

Data Index: 1318827 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 3.4846. Min Range: -3.4846

Max Act: 2.6358. Min Act: -0.0000

Data Index: 561680 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 3.4846. Min Range: -3.4846

Max Act: 2.6755. Min Act: -0.0000

Data Index: 1172160 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 3.4846. Min Range: -3.4846

Max Act: 2.5215. Min Act: -0.0000

Data Index: 102433 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 3.4846. Min Range: -3.4846

Max Act: 2.4485. Min Act: -0.0000

Data Index: 1038795 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 3.4846. Min Range: -3.4846

Max Act: 2.4495. Min Act: -0.0000

Data Index: 633678 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 3.4846. Min Range: -3.4846

Max Act: 2.3232. Min Act: -0.0000

Data Index: 579728 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 3.4846. Min Range: -3.4846

Max Act: 2.4418. Min Act: -0.0000

Data Index: 653819 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 3.4846. Min Range: -3.4846

Max Act: 2.3998. Min Act: -0.0000

Data Index: 296255 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 3.4846. Min Range: -3.4846

Max Act: 2.2465. Min Act: -0.0000

Data Index: 918948 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 3.4846. Min Range: -3.4846

Max Act: 2.4482. Min Act: -0.0000

Data Index: 541499 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 3.4846. Min Range: -3.4846

Max Act: 2.4289. Min Act: -0.0000

Data Index: 760672 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 3.4846. Min Range: -3.4846

Max Act: 2.5889. Min Act: -0.0000

Data Index: 1143089 (C4 (Web Text))

Max Activating Token Index: 198

Text #19

Max Range: 3.4846. Min Range: -3.4846

Max Act: 2.1040. Min Act: -0.0000

Data Index: 260838 (C4 (Web Text))

Max Activating Token Index: 148