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

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

Neuron 2826 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.0343. Min Range: -2.0343

Max Act: 2.0343. Min Act: -0.0002

Data Index: 968503 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 2.0343. Min Range: -2.0343

Max Act: 1.9451. Min Act: -0.0002

Data Index: 954206 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 2.0343. Min Range: -2.0343

Max Act: 1.7678. Min Act: -0.0002

Data Index: 513101 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 2.0343. Min Range: -2.0343

Max Act: 1.7081. Min Act: -0.0002

Data Index: 369610 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 2.0343. Min Range: -2.0343

Max Act: 1.6811. Min Act: -0.0002

Data Index: 594318 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 2.0343. Min Range: -2.0343

Max Act: 1.6897. Min Act: -0.0002

Data Index: 50141 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 2.0343. Min Range: -2.0343

Max Act: 1.6625. Min Act: -0.0002

Data Index: 266776 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 2.0343. Min Range: -2.0343

Max Act: 1.6369. Min Act: -0.0002

Data Index: 251262 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 2.0343. Min Range: -2.0343

Max Act: 1.6198. Min Act: -0.0002

Data Index: 512464 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 2.0343. Min Range: -2.0343

Max Act: 1.6545. Min Act: -0.0002

Data Index: 1127402 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 2.0343. Min Range: -2.0343

Max Act: 1.6539. Min Act: -0.0003

Data Index: 971794 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 2.0343. Min Range: -2.0343

Max Act: 1.6054. Min Act: -0.0002

Data Index: 300802 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 2.0343. Min Range: -2.0343

Max Act: 1.6405. Min Act: -0.0002

Data Index: 1215017 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 2.0343. Min Range: -2.0343

Max Act: 1.6285. Min Act: -0.0002

Data Index: 664862 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 2.0343. Min Range: -2.0343

Max Act: 1.6081. Min Act: -0.0002

Data Index: 767102 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 2.0343. Min Range: -2.0343

Max Act: 1.5772. Min Act: -0.0002

Data Index: 856701 (C4 (Web Text))

Max Activating Token Index: 299

Text #16

Max Range: 2.0343. Min Range: -2.0343

Max Act: 1.5807. Min Act: -0.0002

Data Index: 1171222 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 2.0343. Min Range: -2.0343

Max Act: 1.5847. Min Act: -0.0003

Data Index: 425233 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 2.0343. Min Range: -2.0343

Max Act: 1.5739. Min Act: -0.0002

Data Index: 27322 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 2.0343. Min Range: -2.0343

Max Act: 1.5995. Min Act: -0.0002

Data Index: 722025 (C4 (Web Text))

Max Activating Token Index: 489