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

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

Neuron 2465 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: 0.1509. Min Range: -0.1509

Max Act: 0.1509. Min Act: -0.0002

Data Index: 1056692 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1327. Min Act: -0.0001

Data Index: 908715 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1216. Min Act: -0.0001

Data Index: 339407 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1147. Min Act: -0.0001

Data Index: 869111 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1071. Min Act: -0.0001

Data Index: 1178024 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1063. Min Act: -0.0001

Data Index: 1129688 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1041. Min Act: -0.0001

Data Index: 182165 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0984. Min Act: -0.0001

Data Index: 295852 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0966. Min Act: -0.0001

Data Index: 607792 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0952. Min Act: -0.0001

Data Index: 1075722 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0865. Min Act: -0.0001

Data Index: 561269 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0855. Min Act: -0.0001

Data Index: 346840 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0850. Min Act: -0.0001

Data Index: 615663 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0821. Min Act: -0.0001

Data Index: 373279 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0849. Min Act: -0.0001

Data Index: 275882 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0843. Min Act: -0.0001

Data Index: 160807 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0830. Min Act: -0.0001

Data Index: 616204 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0831. Min Act: -0.0001

Data Index: 463151 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0823. Min Act: -0.0001

Data Index: 1223804 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0818. Min Act: -0.0001

Data Index: 390812 (C4 (Web Text))

Max Activating Token Index: 387