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

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

Neuron 1235 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6145. Min Range: -0.6145

Max Act: 0.6145. Min Act: -0.0000

Data Index: 923967 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 0.6145. Min Range: -0.6145

Max Act: 0.5846. Min Act: -0.0000

Data Index: 590205 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 0.6145. Min Range: -0.6145

Max Act: 0.5440. Min Act: -0.0000

Data Index: 918511 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 0.6145. Min Range: -0.6145

Max Act: 0.5456. Min Act: -0.0000

Data Index: 1336395 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 0.6145. Min Range: -0.6145

Max Act: 0.5269. Min Act: 0.0001

Data Index: 893615 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.6145. Min Range: -0.6145

Max Act: 0.5004. Min Act: -0.0000

Data Index: 378531 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 0.6145. Min Range: -0.6145

Max Act: 0.4909. Min Act: -0.0000

Data Index: 1225120 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 0.6145. Min Range: -0.6145

Max Act: 0.4763. Min Act: -0.0000

Data Index: 1268820 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 0.6145. Min Range: -0.6145

Max Act: 0.4993. Min Act: -0.0000

Data Index: 690447 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 0.6145. Min Range: -0.6145

Max Act: 0.4842. Min Act: -0.0000

Data Index: 1319513 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 0.6145. Min Range: -0.6145

Max Act: 0.4652. Min Act: 0.0000

Data Index: 1056768 (C4 (Web Text))

Max Activating Token Index: 980

Text #11

Max Range: 0.6145. Min Range: -0.6145

Max Act: 0.4900. Min Act: -0.0000

Data Index: 89299 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 0.6145. Min Range: -0.6145

Max Act: 0.4439. Min Act: -0.0000

Data Index: 89428 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 0.6145. Min Range: -0.6145

Max Act: 0.4425. Min Act: -0.0000

Data Index: 641728 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 0.6145. Min Range: -0.6145

Max Act: 0.4567. Min Act: -0.0000

Data Index: 260774 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 0.6145. Min Range: -0.6145

Max Act: 0.4481. Min Act: -0.0000

Data Index: 48420 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 0.6145. Min Range: -0.6145

Max Act: 0.4440. Min Act: -0.0000

Data Index: 984755 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 0.6145. Min Range: -0.6145

Max Act: 0.4255. Min Act: -0.0000

Data Index: 478806 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 0.6145. Min Range: -0.6145

Max Act: 0.4312. Min Act: -0.0000

Data Index: 331110 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 0.6145. Min Range: -0.6145

Max Act: 0.4290. Min Act: -0.0000

Data Index: 805680 (C4 (Web Text))

Max Activating Token Index: 38