Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3474 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.8533. Min Act: -0.0001

Data Index: 1629635 (Python Code)

Max Activating Token Index: 237

Text #1

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.7014. Min Act: -0.0001

Data Index: 411052 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.7044. Min Act: -0.0001

Data Index: 183325 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.7029. Min Act: -0.0000

Data Index: 916370 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.6519. Min Act: -0.0000

Data Index: 479120 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.6093. Min Act: -0.0001

Data Index: 1620869 (Python Code)

Max Activating Token Index: 547

Text #6

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.6737. Min Act: -0.0001

Data Index: 1072341 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.5702. Min Act: -0.0001

Data Index: 106325 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.5127. Min Act: -0.0000

Data Index: 370018 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.6198. Min Act: -0.0001

Data Index: 254120 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.5088. Min Act: -0.0001

Data Index: 1166875 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.5222. Min Act: -0.0001

Data Index: 1344644 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.5191. Min Act: -0.0001

Data Index: 897306 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.5112. Min Act: -0.0000

Data Index: 503101 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.5404. Min Act: -0.0001

Data Index: 406922 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.5179. Min Act: -0.0001

Data Index: 1592468 (Python Code)

Max Activating Token Index: 610

Text #16

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.4930. Min Act: -0.0001

Data Index: 1068923 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.4787. Min Act: -0.0001

Data Index: 579137 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.4828. Min Act: -0.0001

Data Index: 1078683 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.4498. Min Act: -0.0001

Data Index: 910966 (C4 (Web Text))

Max Activating Token Index: 513