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

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

Neuron 71 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: 0.8992. Min Range: -0.8992

Max Act: 0.8992. Min Act: -0.0002

Data Index: 910604 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.8700. Min Act: -0.0002

Data Index: 490543 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.8583. Min Act: -0.0002

Data Index: 362292 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.8672. Min Act: -0.0002

Data Index: 446489 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7912. Min Act: -0.0002

Data Index: 515558 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7644. Min Act: -0.0002

Data Index: 489730 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7690. Min Act: -0.0002

Data Index: 261424 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7271. Min Act: -0.0002

Data Index: 8652 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7214. Min Act: -0.0002

Data Index: 526169 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7334. Min Act: -0.0002

Data Index: 558806 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7423. Min Act: -0.0002

Data Index: 193831 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7089. Min Act: -0.0002

Data Index: 270466 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7104. Min Act: -0.0002

Data Index: 803989 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7067. Min Act: -0.0002

Data Index: 1294435 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7019. Min Act: -0.0002

Data Index: 467320 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7249. Min Act: -0.0002

Data Index: 315798 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7280. Min Act: -0.0002

Data Index: 8479 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7113. Min Act: -0.0002

Data Index: 251681 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.6852. Min Act: -0.0002

Data Index: 689034 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7044. Min Act: -0.0002

Data Index: 1327486 (C4 (Web Text))

Max Activating Token Index: 402