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

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

Neuron 1960 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0488. Min Range: -4.0488

Max Act: 4.0488. Min Act: -0.0000

Data Index: 794792 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 4.0488. Min Range: -4.0488

Max Act: 3.7333. Min Act: -0.0000

Data Index: 1090093 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 4.0488. Min Range: -4.0488

Max Act: 3.7413. Min Act: -0.0000

Data Index: 1351064 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 4.0488. Min Range: -4.0488

Max Act: 3.8481. Min Act: -0.0000

Data Index: 30599 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 4.0488. Min Range: -4.0488

Max Act: 3.6075. Min Act: -0.0000

Data Index: 784748 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 4.0488. Min Range: -4.0488

Max Act: 3.6227. Min Act: -0.0000

Data Index: 768965 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 4.0488. Min Range: -4.0488

Max Act: 3.2698. Min Act: -0.0000

Data Index: 1157868 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 4.0488. Min Range: -4.0488

Max Act: 3.4920. Min Act: -0.0000

Data Index: 564937 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 4.0488. Min Range: -4.0488

Max Act: 3.0961. Min Act: -0.0000

Data Index: 224511 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 4.0488. Min Range: -4.0488

Max Act: 2.9266. Min Act: -0.0000

Data Index: 1147479 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 4.0488. Min Range: -4.0488

Max Act: 3.3095. Min Act: -0.0000

Data Index: 276934 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 4.0488. Min Range: -4.0488

Max Act: 3.2398. Min Act: -0.0000

Data Index: 346017 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 4.0488. Min Range: -4.0488

Max Act: 3.0709. Min Act: -0.0000

Data Index: 1032039 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 4.0488. Min Range: -4.0488

Max Act: 3.0872. Min Act: -0.0000

Data Index: 523040 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 4.0488. Min Range: -4.0488

Max Act: 3.0409. Min Act: -0.0000

Data Index: 605502 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 4.0488. Min Range: -4.0488

Max Act: 3.1801. Min Act: -0.0000

Data Index: 945093 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 4.0488. Min Range: -4.0488

Max Act: 3.2006. Min Act: -0.0000

Data Index: 271049 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 4.0488. Min Range: -4.0488

Max Act: 2.9993. Min Act: -0.0000

Data Index: 265511 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 4.0488. Min Range: -4.0488

Max Act: 2.8583. Min Act: -0.0000

Data Index: 1156817 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 4.0488. Min Range: -4.0488

Max Act: 3.3289. Min Act: -0.0000

Data Index: 867211 (C4 (Web Text))

Max Activating Token Index: 897