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

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

Neuron 4700 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: 1.0714. Min Range: -1.0714

Max Act: 1.0714. Min Act: -0.0000

Data Index: 1083063 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9651. Min Act: -0.0000

Data Index: 1161621 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9337. Min Act: -0.0000

Data Index: 450503 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9700. Min Act: -0.0000

Data Index: 1080400 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9259. Min Act: -0.0000

Data Index: 1028052 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.8843. Min Act: -0.0000

Data Index: 1171594 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.8318. Min Act: -0.0000

Data Index: 633973 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.8844. Min Act: 0.0000

Data Index: 870586 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.8569. Min Act: -0.0000

Data Index: 310359 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.8500. Min Act: -0.0000

Data Index: 1159756 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.8116. Min Act: -0.0000

Data Index: 330456 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.8821. Min Act: -0.0000

Data Index: 877141 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.7656. Min Act: -0.0000

Data Index: 157294 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.8104. Min Act: -0.0000

Data Index: 526551 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.7586. Min Act: -0.0000

Data Index: 388210 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.7960. Min Act: -0.0000

Data Index: 1257777 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.7769. Min Act: -0.0000

Data Index: 1027994 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.7700. Min Act: -0.0000

Data Index: 521243 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.7869. Min Act: -0.0000

Data Index: 131416 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.7737. Min Act: 0.0001

Data Index: 1322402 (C4 (Web Text))

Max Activating Token Index: 257