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

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

Neuron 440 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.7464. Min Act: -0.0000

Data Index: 593901 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.7142. Min Act: -0.0000

Data Index: 258228 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.7323. Min Act: -0.0000

Data Index: 996579 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.6414. Min Act: -0.0000

Data Index: 1313501 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.5774. Min Act: -0.0000

Data Index: 449855 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.5353. Min Act: -0.0000

Data Index: 878996 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.5760. Min Act: -0.0000

Data Index: 442305 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.4825. Min Act: -0.0000

Data Index: 1311100 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.4421. Min Act: -0.0000

Data Index: 641823 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.4430. Min Act: -0.0000

Data Index: 583791 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.3937. Min Act: -0.0000

Data Index: 1228461 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.4430. Min Act: -0.0000

Data Index: 582669 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.4424. Min Act: -0.0000

Data Index: 539274 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.3917. Min Act: -0.0000

Data Index: 290261 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.4394. Min Act: -0.0000

Data Index: 589395 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.4677. Min Act: -0.0000

Data Index: 467225 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.3988. Min Act: -0.0000

Data Index: 406233 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.3734. Min Act: -0.0000

Data Index: 943285 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.3580. Min Act: -0.0000

Data Index: 156534 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.3709. Min Act: -0.0000

Data Index: 1022375 (C4 (Web Text))

Max Activating Token Index: 662