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

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

Neuron 1740 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7129. Min Range: -4.7129

Max Act: 4.7129. Min Act: -0.0000

Data Index: 469128 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 4.7129. Min Range: -4.7129

Max Act: 4.0885. Min Act: -0.0000

Data Index: 389528 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 4.7129. Min Range: -4.7129

Max Act: 3.6699. Min Act: -0.0000

Data Index: 1214972 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 4.7129. Min Range: -4.7129

Max Act: 3.6659. Min Act: -0.0000

Data Index: 560789 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 4.7129. Min Range: -4.7129

Max Act: 3.4892. Min Act: -0.0000

Data Index: 142379 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 4.7129. Min Range: -4.7129

Max Act: 3.4680. Min Act: -0.0000

Data Index: 963532 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 4.7129. Min Range: -4.7129

Max Act: 3.6030. Min Act: -0.0000

Data Index: 779615 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 4.7129. Min Range: -4.7129

Max Act: 3.4565. Min Act: -0.0000

Data Index: 785174 (C4 (Web Text))

Max Activating Token Index: 584

Text #8

Max Range: 4.7129. Min Range: -4.7129

Max Act: 3.5133. Min Act: -0.0000

Data Index: 58716 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 4.7129. Min Range: -4.7129

Max Act: 3.4797. Min Act: -0.0000

Data Index: 1076767 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 4.7129. Min Range: -4.7129

Max Act: 3.4451. Min Act: -0.0000

Data Index: 731989 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 4.7129. Min Range: -4.7129

Max Act: 3.1226. Min Act: -0.0000

Data Index: 352406 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 4.7129. Min Range: -4.7129

Max Act: 3.4285. Min Act: -0.0000

Data Index: 820347 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 4.7129. Min Range: -4.7129

Max Act: 3.2491. Min Act: -0.0000

Data Index: 1307526 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 4.7129. Min Range: -4.7129

Max Act: 3.1377. Min Act: -0.0000

Data Index: 962016 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 4.7129. Min Range: -4.7129

Max Act: 3.1009. Min Act: -0.0000

Data Index: 497223 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 4.7129. Min Range: -4.7129

Max Act: 3.0605. Min Act: -0.0000

Data Index: 343810 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 4.7129. Min Range: -4.7129

Max Act: 2.9005. Min Act: -0.0000

Data Index: 391775 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 4.7129. Min Range: -4.7129

Max Act: 3.1653. Min Act: -0.0000

Data Index: 327661 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 4.7129. Min Range: -4.7129

Max Act: 3.1701. Min Act: -0.0000

Data Index: 758558 (C4 (Web Text))

Max Activating Token Index: 192