Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 367 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.3144. Min Act: -0.0001

Data Index: 1028499 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2552. Min Act: -0.0001

Data Index: 742245 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2550. Min Act: -0.0001

Data Index: 974679 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2338. Min Act: -0.0001

Data Index: 1262057 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1818. Min Act: -0.0001

Data Index: 1202345 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2305. Min Act: -0.0001

Data Index: 260754 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1971. Min Act: -0.0001

Data Index: 1138573 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1924. Min Act: -0.0001

Data Index: 894001 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1897. Min Act: -0.0001

Data Index: 192361 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1768. Min Act: -0.0001

Data Index: 1036522 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1881. Min Act: -0.0001

Data Index: 609874 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1794. Min Act: -0.0001

Data Index: 905126 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1689. Min Act: -0.0001

Data Index: 709044 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1835. Min Act: -0.0001

Data Index: 1211170 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1849. Min Act: -0.0001

Data Index: 911419 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1888. Min Act: -0.0001

Data Index: 1202726 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1787. Min Act: -0.0001

Data Index: 319745 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1682. Min Act: -0.0001

Data Index: 163632 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1618. Min Act: -0.0001

Data Index: 1338176 (C4 (Web Text))

Max Activating Token Index: 498

Text #19

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1663. Min Act: -0.0001

Data Index: 327661 (C4 (Web Text))

Max Activating Token Index: 35