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

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

Neuron 1188 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8897. Min Range: -2.8897

Max Act: 2.8897. Min Act: -0.0000

Data Index: 1211155 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 2.8897. Min Range: -2.8897

Max Act: 2.2167. Min Act: -0.0000

Data Index: 501270 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 2.8897. Min Range: -2.8897

Max Act: 1.8904. Min Act: -0.0000

Data Index: 497079 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 2.8897. Min Range: -2.8897

Max Act: 1.9352. Min Act: -0.0000

Data Index: 521364 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 2.8897. Min Range: -2.8897

Max Act: 1.8084. Min Act: -0.0000

Data Index: 90901 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 2.8897. Min Range: -2.8897

Max Act: 1.6780. Min Act: -0.0000

Data Index: 392021 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 2.8897. Min Range: -2.8897

Max Act: 1.8692. Min Act: -0.0000

Data Index: 366688 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 2.8897. Min Range: -2.8897

Max Act: 1.6819. Min Act: -0.0000

Data Index: 896511 (C4 (Web Text))

Max Activating Token Index: 461

Text #8

Max Range: 2.8897. Min Range: -2.8897

Max Act: 1.6727. Min Act: -0.0000

Data Index: 559433 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 2.8897. Min Range: -2.8897

Max Act: 1.8367. Min Act: -0.0000

Data Index: 1346034 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 2.8897. Min Range: -2.8897

Max Act: 1.5740. Min Act: -0.0000

Data Index: 1132481 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 2.8897. Min Range: -2.8897

Max Act: 1.5176. Min Act: -0.0000

Data Index: 730676 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 2.8897. Min Range: -2.8897

Max Act: 1.5581. Min Act: -0.0000

Data Index: 928850 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 2.8897. Min Range: -2.8897

Max Act: 1.4747. Min Act: -0.0000

Data Index: 554189 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 2.8897. Min Range: -2.8897

Max Act: 1.3885. Min Act: -0.0000

Data Index: 1139954 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 2.8897. Min Range: -2.8897

Max Act: 1.5664. Min Act: -0.0000

Data Index: 998208 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 2.8897. Min Range: -2.8897

Max Act: 1.3836. Min Act: -0.0000

Data Index: 660216 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 2.8897. Min Range: -2.8897

Max Act: 1.4145. Min Act: -0.0000

Data Index: 612147 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 2.8897. Min Range: -2.8897

Max Act: 1.3184. Min Act: -0.0000

Data Index: 243294 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 2.8897. Min Range: -2.8897

Max Act: 1.4858. Min Act: -0.0000

Data Index: 84596 (C4 (Web Text))

Max Activating Token Index: 565