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

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

Neuron 3651 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.9119. Min Act: -0.0000

Data Index: 509026 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.9531. Min Act: -0.0000

Data Index: 49512 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8568. Min Act: -0.0000

Data Index: 50761 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7667. Min Act: -0.0000

Data Index: 350479 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7870. Min Act: -0.0000

Data Index: 385790 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7634. Min Act: -0.0000

Data Index: 454997 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7920. Min Act: -0.0000

Data Index: 1308010 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7323. Min Act: -0.0000

Data Index: 137431 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7051. Min Act: -0.0000

Data Index: 199966 (C4 (Web Text))

Max Activating Token Index: 795

Text #9

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.6571. Min Act: -0.0000

Data Index: 958990 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7068. Min Act: -0.0000

Data Index: 469383 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.6852. Min Act: -0.0000

Data Index: 1240602 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.6962. Min Act: -0.0000

Data Index: 1104501 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.6613. Min Act: -0.0000

Data Index: 6849 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.6392. Min Act: -0.0000

Data Index: 289986 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.6809. Min Act: -0.0000

Data Index: 607762 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.6154. Min Act: -0.0000

Data Index: 533090 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.6270. Min Act: -0.0000

Data Index: 1172288 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.5822. Min Act: -0.0000

Data Index: 583086 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.5782. Min Act: -0.0000

Data Index: 511583 (C4 (Web Text))

Max Activating Token Index: 315