Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4965 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.9691. Min Range: -3.9691

Max Act: 3.9691. Min Act: -0.0000

Data Index: 893196 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 3.9691. Min Range: -3.9691

Max Act: 3.3162. Min Act: -0.0000

Data Index: 970485 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 3.9691. Min Range: -3.9691

Max Act: 3.4204. Min Act: -0.0000

Data Index: 401803 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 3.9691. Min Range: -3.9691

Max Act: 3.0512. Min Act: -0.0000

Data Index: 1275224 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 3.9691. Min Range: -3.9691

Max Act: 3.0143. Min Act: -0.0000

Data Index: 925530 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 3.9691. Min Range: -3.9691

Max Act: 2.7012. Min Act: -0.0000

Data Index: 464471 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 3.9691. Min Range: -3.9691

Max Act: 2.4817. Min Act: -0.0000

Data Index: 233849 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 3.9691. Min Range: -3.9691

Max Act: 2.7258. Min Act: -0.0000

Data Index: 586436 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 3.9691. Min Range: -3.9691

Max Act: 2.5650. Min Act: -0.0000

Data Index: 210682 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 3.9691. Min Range: -3.9691

Max Act: 2.5635. Min Act: -0.0000

Data Index: 919791 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 3.9691. Min Range: -3.9691

Max Act: 2.6910. Min Act: -0.0000

Data Index: 1045539 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 3.9691. Min Range: -3.9691

Max Act: 2.6816. Min Act: -0.0000

Data Index: 724400 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 3.9691. Min Range: -3.9691

Max Act: 2.7955. Min Act: -0.0000

Data Index: 179973 (C4 (Web Text))

Max Activating Token Index: 623

Text #13

Max Range: 3.9691. Min Range: -3.9691

Max Act: 2.6140. Min Act: -0.0000

Data Index: 690910 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 3.9691. Min Range: -3.9691

Max Act: 2.5851. Min Act: -0.0000

Data Index: 1614576 (Python Code)

Max Activating Token Index: 42

Text #15

Max Range: 3.9691. Min Range: -3.9691

Max Act: 2.5551. Min Act: -0.0000

Data Index: 428728 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 3.9691. Min Range: -3.9691

Max Act: 2.4405. Min Act: -0.0000

Data Index: 1488273 (Python Code)

Max Activating Token Index: 488

Text #17

Max Range: 3.9691. Min Range: -3.9691

Max Act: 2.5381. Min Act: -0.0000

Data Index: 7962 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 3.9691. Min Range: -3.9691

Max Act: 2.5144. Min Act: -0.0000

Data Index: 1135838 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 3.9691. Min Range: -3.9691

Max Act: 2.3748. Min Act: -0.0000

Data Index: 1556831 (Python Code)

Max Activating Token Index: 923