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

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

Neuron 2562 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9738. Min Range: -1.9738

Max Act: 1.9738. Min Act: -0.0000

Data Index: 758351 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 1.9738. Min Range: -1.9738

Max Act: 1.6613. Min Act: -0.0000

Data Index: 769364 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 1.9738. Min Range: -1.9738

Max Act: 1.6545. Min Act: -0.0000

Data Index: 3098 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 1.9738. Min Range: -1.9738

Max Act: 1.5229. Min Act: -0.0000

Data Index: 1191554 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 1.9738. Min Range: -1.9738

Max Act: 1.4378. Min Act: -0.0000

Data Index: 929584 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 1.9738. Min Range: -1.9738

Max Act: 1.4730. Min Act: -0.0000

Data Index: 50053 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 1.9738. Min Range: -1.9738

Max Act: 1.4148. Min Act: -0.0000

Data Index: 1082200 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 1.9738. Min Range: -1.9738

Max Act: 1.4125. Min Act: -0.0000

Data Index: 450323 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 1.9738. Min Range: -1.9738

Max Act: 1.4157. Min Act: -0.0000

Data Index: 1034638 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 1.9738. Min Range: -1.9738

Max Act: 1.4037. Min Act: -0.0000

Data Index: 922186 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 1.9738. Min Range: -1.9738

Max Act: 1.4015. Min Act: -0.0000

Data Index: 153289 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 1.9738. Min Range: -1.9738

Max Act: 1.3861. Min Act: -0.0000

Data Index: 758647 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 1.9738. Min Range: -1.9738

Max Act: 1.3532. Min Act: -0.0000

Data Index: 728176 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 1.9738. Min Range: -1.9738

Max Act: 1.4275. Min Act: -0.0000

Data Index: 293534 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 1.9738. Min Range: -1.9738

Max Act: 1.4307. Min Act: -0.0000

Data Index: 964711 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 1.9738. Min Range: -1.9738

Max Act: 1.4103. Min Act: -0.0000

Data Index: 261882 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 1.9738. Min Range: -1.9738

Max Act: 1.3667. Min Act: -0.0000

Data Index: 317978 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 1.9738. Min Range: -1.9738

Max Act: 1.3280. Min Act: -0.0000

Data Index: 433231 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 1.9738. Min Range: -1.9738

Max Act: 1.4089. Min Act: -0.0000

Data Index: 464770 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 1.9738. Min Range: -1.9738

Max Act: 1.2816. Min Act: -0.0000

Data Index: 690779 (C4 (Web Text))

Max Activating Token Index: 822