Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3591 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.4179. Min Act: -0.0001

Data Index: 655271 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.3280. Min Act: -0.0001

Data Index: 40233 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.3022. Min Act: -0.0001

Data Index: 850408 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.3091. Min Act: -0.0001

Data Index: 182951 (C4 (Web Text))

Max Activating Token Index: 388

Text #4

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2830. Min Act: -0.0001

Data Index: 272475 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2996. Min Act: -0.0001

Data Index: 734586 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.3152. Min Act: -0.0001

Data Index: 656506 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2751. Min Act: -0.0001

Data Index: 931944 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2750. Min Act: -0.0001

Data Index: 1260252 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2672. Min Act: -0.0001

Data Index: 1021242 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2423. Min Act: -0.0001

Data Index: 411867 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2719. Min Act: -0.0001

Data Index: 1046741 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2366. Min Act: -0.0001

Data Index: 999156 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2700. Min Act: -0.0001

Data Index: 1066708 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2516. Min Act: -0.0001

Data Index: 1241694 (C4 (Web Text))

Max Activating Token Index: 855

Text #15

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2674. Min Act: -0.0002

Data Index: 811526 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2363. Min Act: -0.0001

Data Index: 415485 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2394. Min Act: -0.0001

Data Index: 722313 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2290. Min Act: -0.0001

Data Index: 1269250 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2339. Min Act: -0.0001

Data Index: 1003231 (C4 (Web Text))

Max Activating Token Index: 79