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

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

Neuron 1333 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.3900. Min Act: -0.0001

Data Index: 1090773 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2217. Min Act: -0.0001

Data Index: 861281 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2065. Min Act: -0.0001

Data Index: 748499 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.1987. Min Act: -0.0001

Data Index: 195745 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2019. Min Act: -0.0001

Data Index: 747051 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.1906. Min Act: -0.0001

Data Index: 845496 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.1774. Min Act: -0.0001

Data Index: 990707 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.1642. Min Act: -0.0001

Data Index: 319155 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.1658. Min Act: -0.0001

Data Index: 483744 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.1592. Min Act: -0.0001

Data Index: 1154587 (C4 (Web Text))

Max Activating Token Index: 914

Text #10

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.1596. Min Act: -0.0001

Data Index: 1056015 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.1728. Min Act: -0.0001

Data Index: 439156 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.1629. Min Act: -0.0001

Data Index: 128576 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.1458. Min Act: -0.0001

Data Index: 1136777 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.1559. Min Act: -0.0001

Data Index: 279799 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.1418. Min Act: -0.0001

Data Index: 693512 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.1495. Min Act: -0.0001

Data Index: 1333996 (C4 (Web Text))

Max Activating Token Index: 416

Text #17

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.1532. Min Act: -0.0001

Data Index: 167912 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.1438. Min Act: -0.0001

Data Index: 807603 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.1430. Min Act: -0.0001

Data Index: 1098629 (C4 (Web Text))

Max Activating Token Index: 179