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

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

Neuron 4488 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: 1.7807. Min Range: -1.7807

Max Act: 1.7807. Min Act: -0.0002

Data Index: 918117 (C4 (Web Text))

Max Activating Token Index: 820

Text #1

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.6123. Min Act: -0.0002

Data Index: 1268362 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.4594. Min Act: -0.0002

Data Index: 1315880 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.4631. Min Act: -0.0002

Data Index: 884087 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.4715. Min Act: -0.0002

Data Index: 480210 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.4259. Min Act: -0.0003

Data Index: 1328259 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.4689. Min Act: -0.0002

Data Index: 1263039 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.3850. Min Act: -0.0002

Data Index: 1064953 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.3775. Min Act: -0.0002

Data Index: 165748 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.3432. Min Act: -0.0002

Data Index: 299674 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.3232. Min Act: -0.0002

Data Index: 952467 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.2970. Min Act: -0.0002

Data Index: 366876 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.3272. Min Act: -0.0002

Data Index: 203155 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.2907. Min Act: -0.0002

Data Index: 173424 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.3115. Min Act: -0.0002

Data Index: 75451 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.3045. Min Act: -0.0002

Data Index: 328222 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.2878. Min Act: -0.0002

Data Index: 586366 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.2818. Min Act: -0.0002

Data Index: 278469 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.2807. Min Act: -0.0002

Data Index: 611998 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.2151. Min Act: -0.0002

Data Index: 692009 (C4 (Web Text))

Max Activating Token Index: 419