Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3042 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6081. Min Range: -0.6081

Max Act: 0.6081. Min Act: -0.0001

Data Index: 603604 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.6081. Min Range: -0.6081

Max Act: 0.5586. Min Act: -0.0001

Data Index: 838531 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 0.6081. Min Range: -0.6081

Max Act: 0.5143. Min Act: -0.0001

Data Index: 1214611 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 0.6081. Min Range: -0.6081

Max Act: 0.5707. Min Act: -0.0001

Data Index: 865350 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 0.6081. Min Range: -0.6081

Max Act: 0.5188. Min Act: -0.0001

Data Index: 914308 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 0.6081. Min Range: -0.6081

Max Act: 0.5083. Min Act: -0.0001

Data Index: 623465 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 0.6081. Min Range: -0.6081

Max Act: 0.5301. Min Act: -0.0001

Data Index: 491168 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.6081. Min Range: -0.6081

Max Act: 0.5623. Min Act: -0.0001

Data Index: 576705 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 0.6081. Min Range: -0.6081

Max Act: 0.5415. Min Act: -0.0001

Data Index: 661282 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 0.6081. Min Range: -0.6081

Max Act: 0.5357. Min Act: -0.0001

Data Index: 777910 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 0.6081. Min Range: -0.6081

Max Act: 0.5479. Min Act: -0.0001

Data Index: 882549 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 0.6081. Min Range: -0.6081

Max Act: 0.5125. Min Act: -0.0001

Data Index: 1087384 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 0.6081. Min Range: -0.6081

Max Act: 0.4802. Min Act: -0.0001

Data Index: 619998 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 0.6081. Min Range: -0.6081

Max Act: 0.5326. Min Act: -0.0001

Data Index: 697725 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 0.6081. Min Range: -0.6081

Max Act: 0.5163. Min Act: -0.0001

Data Index: 684594 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 0.6081. Min Range: -0.6081

Max Act: 0.4946. Min Act: -0.0001

Data Index: 1039648 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 0.6081. Min Range: -0.6081

Max Act: 0.4932. Min Act: -0.0001

Data Index: 731323 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 0.6081. Min Range: -0.6081

Max Act: 0.4911. Min Act: -0.0001

Data Index: 329848 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 0.6081. Min Range: -0.6081

Max Act: 0.4678. Min Act: -0.0001

Data Index: 344156 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 0.6081. Min Range: -0.6081

Max Act: 0.4617. Min Act: -0.0001

Data Index: 1150333 (C4 (Web Text))

Max Activating Token Index: 965