Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 67 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2039. Min Range: -1.2039

Max Act: 1.2039. Min Act: -0.0001

Data Index: 1517178 (Python Code)

Max Activating Token Index: 534

Text #1

Max Range: 1.2039. Min Range: -1.2039

Max Act: 1.1175. Min Act: -0.0001

Data Index: 1645310 (Python Code)

Max Activating Token Index: 285

Text #2

Max Range: 1.2039. Min Range: -1.2039

Max Act: 1.1049. Min Act: -0.0001

Data Index: 636097 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 1.2039. Min Range: -1.2039

Max Act: 1.0749. Min Act: -0.0001

Data Index: 718877 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 1.2039. Min Range: -1.2039

Max Act: 1.0479. Min Act: -0.0001

Data Index: 315432 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 1.2039. Min Range: -1.2039

Max Act: 0.9750. Min Act: -0.0001

Data Index: 1307912 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 1.2039. Min Range: -1.2039

Max Act: 0.9927. Min Act: -0.0001

Data Index: 879608 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 1.2039. Min Range: -1.2039

Max Act: 0.9461. Min Act: -0.0001

Data Index: 661291 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 1.2039. Min Range: -1.2039

Max Act: 0.9667. Min Act: -0.0001

Data Index: 286984 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 1.2039. Min Range: -1.2039

Max Act: 0.9773. Min Act: -0.0001

Data Index: 491285 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 1.2039. Min Range: -1.2039

Max Act: 0.9864. Min Act: -0.0001

Data Index: 1547293 (Python Code)

Max Activating Token Index: 214

Text #11

Max Range: 1.2039. Min Range: -1.2039

Max Act: 0.9602. Min Act: -0.0001

Data Index: 634288 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 1.2039. Min Range: -1.2039

Max Act: 0.9007. Min Act: -0.0001

Data Index: 1543630 (Python Code)

Max Activating Token Index: 254

Text #13

Max Range: 1.2039. Min Range: -1.2039

Max Act: 0.8791. Min Act: -0.0001

Data Index: 1472505 (Python Code)

Max Activating Token Index: 525

Text #14

Max Range: 1.2039. Min Range: -1.2039

Max Act: 0.9414. Min Act: -0.0001

Data Index: 437954 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 1.2039. Min Range: -1.2039

Max Act: 0.8735. Min Act: -0.0001

Data Index: 1467186 (Python Code)

Max Activating Token Index: 72

Text #16

Max Range: 1.2039. Min Range: -1.2039

Max Act: 0.8043. Min Act: -0.0001

Data Index: 1433536 (Python Code)

Max Activating Token Index: 769

Text #17

Max Range: 1.2039. Min Range: -1.2039

Max Act: 0.9069. Min Act: -0.0001

Data Index: 398251 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 1.2039. Min Range: -1.2039

Max Act: 0.8907. Min Act: -0.0001

Data Index: 394872 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 1.2039. Min Range: -1.2039

Max Act: 0.8559. Min Act: -0.0001

Data Index: 1598275 (Python Code)

Max Activating Token Index: 123