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

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

Neuron 1531 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.8377. Min Act: -0.0000

Data Index: 4437 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.5342. Min Act: -0.0000

Data Index: 476196 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.4445. Min Act: -0.0000

Data Index: 431303 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.4403. Min Act: -0.0000

Data Index: 245394 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.4312. Min Act: -0.0000

Data Index: 1011995 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.3801. Min Act: -0.0000

Data Index: 272668 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.3444. Min Act: -0.0000

Data Index: 240600 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.4929. Min Act: -0.0000

Data Index: 166578 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.4456. Min Act: -0.0000

Data Index: 1050994 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.3722. Min Act: -0.0000

Data Index: 1201623 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.4318. Min Act: -0.0000

Data Index: 144833 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.3327. Min Act: -0.0000

Data Index: 269236 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.3468. Min Act: -0.0000

Data Index: 776564 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.2314. Min Act: -0.0000

Data Index: 1318141 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.3798. Min Act: -0.0000

Data Index: 241826 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.4169. Min Act: -0.0000

Data Index: 455165 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.3125. Min Act: -0.0000

Data Index: 1190241 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.3009. Min Act: -0.0000

Data Index: 641850 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.2575. Min Act: -0.0000

Data Index: 22453 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 1.8377. Min Range: -1.8377

Max Act: 1.3412. Min Act: -0.0000

Data Index: 743547 (C4 (Web Text))

Max Activating Token Index: 46