Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 430 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.7278. Min Act: -0.0000

Data Index: 834011 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6583. Min Act: -0.0000

Data Index: 475244 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6228. Min Act: -0.0000

Data Index: 513313 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5557. Min Act: -0.0000

Data Index: 836159 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5515. Min Act: -0.0000

Data Index: 683689 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5338. Min Act: -0.0001

Data Index: 1016631 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5107. Min Act: -0.0000

Data Index: 438434 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4951. Min Act: -0.0001

Data Index: 157548 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5075. Min Act: -0.0001

Data Index: 1253019 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4875. Min Act: -0.0000

Data Index: 331338 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5208. Min Act: -0.0000

Data Index: 511355 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4844. Min Act: -0.0000

Data Index: 83307 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5151. Min Act: -0.0000

Data Index: 1299032 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4865. Min Act: -0.0001

Data Index: 1233747 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4810. Min Act: -0.0000

Data Index: 1349465 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4941. Min Act: -0.0001

Data Index: 180373 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5050. Min Act: -0.0000

Data Index: 749380 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4930. Min Act: -0.0001

Data Index: 967797 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4676. Min Act: -0.0001

Data Index: 804712 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4691. Min Act: -0.0000

Data Index: 711736 (C4 (Web Text))

Max Activating Token Index: 137