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

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

Neuron 2538 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.7773. Min Act: -0.0001

Data Index: 231883 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.8416. Min Act: -0.0001

Data Index: 344156 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.6591. Min Act: -0.0001

Data Index: 904514 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.5627. Min Act: -0.0001

Data Index: 1272930 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.5828. Min Act: -0.0001

Data Index: 1106057 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.5951. Min Act: -0.0001

Data Index: 699996 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.4753. Min Act: -0.0001

Data Index: 28984 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.5693. Min Act: -0.0001

Data Index: 984118 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.5235. Min Act: -0.0001

Data Index: 1116039 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.5154. Min Act: -0.0001

Data Index: 1125115 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.4677. Min Act: -0.0001

Data Index: 99443 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.5176. Min Act: -0.0001

Data Index: 242637 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.5153. Min Act: -0.0001

Data Index: 135746 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.5252. Min Act: -0.0001

Data Index: 763878 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.4748. Min Act: -0.0001

Data Index: 408603 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.5269. Min Act: -0.0001

Data Index: 841564 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.4861. Min Act: -0.0001

Data Index: 519969 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.5156. Min Act: -0.0001

Data Index: 117174 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.4702. Min Act: -0.0001

Data Index: 759215 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.4596. Min Act: -0.0001

Data Index: 1295032 (C4 (Web Text))

Max Activating Token Index: 914