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

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

Neuron 2376 in Layer 0

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: 0.6009. Min Range: -0.6009

Max Act: 0.6009. Min Act: -0.0001

Data Index: 1060209 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.5624. Min Act: -0.0001

Data Index: 498501 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.5568. Min Act: -0.0001

Data Index: 178520 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.5522. Min Act: -0.0001

Data Index: 474856 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.5235. Min Act: -0.0001

Data Index: 951762 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.5180. Min Act: -0.0002

Data Index: 218794 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.5047. Min Act: -0.0001

Data Index: 432540 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.5103. Min Act: -0.0001

Data Index: 1111476 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4891. Min Act: -0.0001

Data Index: 1101651 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4936. Min Act: -0.0001

Data Index: 839639 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4978. Min Act: -0.0001

Data Index: 96042 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4930. Min Act: -0.0001

Data Index: 216861 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4806. Min Act: -0.0001

Data Index: 996672 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4829. Min Act: -0.0001

Data Index: 787615 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4860. Min Act: -0.0001

Data Index: 233510 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4904. Min Act: -0.0001

Data Index: 952916 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4813. Min Act: -0.0001

Data Index: 101479 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4826. Min Act: -0.0001

Data Index: 412143 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4818. Min Act: -0.0001

Data Index: 1031837 (C4 (Web Text))

Max Activating Token Index: 652

Text #19

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4741. Min Act: -0.0001

Data Index: 832286 (C4 (Web Text))

Max Activating Token Index: 173