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

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

Neuron 5014 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4947. Min Range: -0.4947

Max Act: 0.4947. Min Act: -0.0000

Data Index: 949835 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 0.4947. Min Range: -0.4947

Max Act: 0.4822. Min Act: -0.0000

Data Index: 892758 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 0.4947. Min Range: -0.4947

Max Act: 0.4194. Min Act: -0.0000

Data Index: 1119620 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 0.4947. Min Range: -0.4947

Max Act: 0.4442. Min Act: 0.0000

Data Index: 1244044 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 0.4947. Min Range: -0.4947

Max Act: 0.4135. Min Act: -0.0000

Data Index: 535469 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 0.4947. Min Range: -0.4947

Max Act: 0.4314. Min Act: -0.0000

Data Index: 639069 (C4 (Web Text))

Max Activating Token Index: 606

Text #6

Max Range: 0.4947. Min Range: -0.4947

Max Act: 0.3861. Min Act: -0.0000

Data Index: 907683 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 0.4947. Min Range: -0.4947

Max Act: 0.3708. Min Act: -0.0000

Data Index: 764892 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 0.4947. Min Range: -0.4947

Max Act: 0.3590. Min Act: -0.0000

Data Index: 1270581 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 0.4947. Min Range: -0.4947

Max Act: 0.3549. Min Act: -0.0000

Data Index: 438697 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 0.4947. Min Range: -0.4947

Max Act: 0.3410. Min Act: -0.0000

Data Index: 86201 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 0.4947. Min Range: -0.4947

Max Act: 0.3243. Min Act: -0.0000

Data Index: 1129843 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 0.4947. Min Range: -0.4947

Max Act: 0.3513. Min Act: -0.0000

Data Index: 549828 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 0.4947. Min Range: -0.4947

Max Act: 0.3040. Min Act: -0.0000

Data Index: 375276 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 0.4947. Min Range: -0.4947

Max Act: 0.3096. Min Act: -0.0000

Data Index: 1348640 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 0.4947. Min Range: -0.4947

Max Act: 0.2968. Min Act: -0.0000

Data Index: 18313 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 0.4947. Min Range: -0.4947

Max Act: 0.3113. Min Act: -0.0000

Data Index: 242591 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.4947. Min Range: -0.4947

Max Act: 0.3085. Min Act: -0.0000

Data Index: 1056504 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 0.4947. Min Range: -0.4947

Max Act: 0.2853. Min Act: 0.0000

Data Index: 101855 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 0.4947. Min Range: -0.4947

Max Act: 0.2853. Min Act: 0.0000

Data Index: 836382 (C4 (Web Text))

Max Activating Token Index: 349