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

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

Neuron 4245 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.5393. Min Act: -0.0001

Data Index: 857058 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.4370. Min Act: -0.0001

Data Index: 853473 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.4112. Min Act: -0.0001

Data Index: 562346 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.3672. Min Act: -0.0000

Data Index: 695530 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.3752. Min Act: -0.0001

Data Index: 570258 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.4019. Min Act: -0.0001

Data Index: 308921 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.3481. Min Act: -0.0001

Data Index: 510583 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.3631. Min Act: -0.0000

Data Index: 1227548 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.3289. Min Act: -0.0001

Data Index: 120696 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.3293. Min Act: -0.0001

Data Index: 949089 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.2975. Min Act: -0.0000

Data Index: 497067 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.2565. Min Act: -0.0001

Data Index: 954828 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.3184. Min Act: -0.0001

Data Index: 665844 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.2966. Min Act: -0.0001

Data Index: 1193511 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.3356. Min Act: -0.0001

Data Index: 626487 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.3048. Min Act: -0.0001

Data Index: 440291 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.3178. Min Act: -0.0001

Data Index: 221123 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.3077. Min Act: -0.0001

Data Index: 644816 (C4 (Web Text))

Max Activating Token Index: 514

Text #18

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.3115. Min Act: -0.0001

Data Index: 1057632 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.3158. Min Act: -0.0001

Data Index: 1139888 (C4 (Web Text))

Max Activating Token Index: 291