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

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

Neuron 2719 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: 0.0965. Min Range: -0.0965

Max Act: 0.0965. Min Act: -0.0002

Data Index: 1316736 (C4 (Web Text))

Max Activating Token Index: 632

Text #1

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0925. Min Act: -0.0002

Data Index: 468023 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0913. Min Act: -0.0002

Data Index: 683983 (C4 (Web Text))

Max Activating Token Index: 450

Text #3

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0927. Min Act: -0.0002

Data Index: 35779 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0924. Min Act: -0.0002

Data Index: 915745 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0924. Min Act: -0.0002

Data Index: 72850 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0891. Min Act: -0.0002

Data Index: 1218861 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0876. Min Act: -0.0002

Data Index: 422351 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0889. Min Act: -0.0002

Data Index: 796153 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0860. Min Act: -0.0002

Data Index: 27004 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0862. Min Act: -0.0002

Data Index: 711534 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0867. Min Act: -0.0002

Data Index: 734129 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0854. Min Act: -0.0002

Data Index: 661827 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0841. Min Act: -0.0002

Data Index: 655094 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0861. Min Act: -0.0002

Data Index: 1306624 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0855. Min Act: -0.0002

Data Index: 1038283 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0864. Min Act: -0.0002

Data Index: 197951 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0856. Min Act: -0.0002

Data Index: 886405 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0848. Min Act: -0.0002

Data Index: 1199433 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0860. Min Act: -0.0002

Data Index: 526023 (C4 (Web Text))

Max Activating Token Index: 131