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

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

Neuron 4548 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1162. Min Range: -1.1162

Max Act: 1.1162. Min Act: -0.0000

Data Index: 819675 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 1.1162. Min Range: -1.1162

Max Act: 0.8916. Min Act: -0.0000

Data Index: 990452 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 1.1162. Min Range: -1.1162

Max Act: 0.8868. Min Act: -0.0000

Data Index: 714785 (C4 (Web Text))

Max Activating Token Index: 412

Text #3

Max Range: 1.1162. Min Range: -1.1162

Max Act: 0.8964. Min Act: -0.0000

Data Index: 55191 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 1.1162. Min Range: -1.1162

Max Act: 0.6921. Min Act: -0.0000

Data Index: 708912 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 1.1162. Min Range: -1.1162

Max Act: 0.7337. Min Act: -0.0000

Data Index: 611915 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 1.1162. Min Range: -1.1162

Max Act: 0.6683. Min Act: -0.0000

Data Index: 1227909 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 1.1162. Min Range: -1.1162

Max Act: 0.6720. Min Act: -0.0000

Data Index: 1358433 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 1.1162. Min Range: -1.1162

Max Act: 0.6459. Min Act: -0.0000

Data Index: 891286 (C4 (Web Text))

Max Activating Token Index: 481

Text #9

Max Range: 1.1162. Min Range: -1.1162

Max Act: 0.5836. Min Act: -0.0000

Data Index: 834897 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 1.1162. Min Range: -1.1162

Max Act: 0.5939. Min Act: -0.0000

Data Index: 596138 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 1.1162. Min Range: -1.1162

Max Act: 0.6155. Min Act: -0.0000

Data Index: 429878 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 1.1162. Min Range: -1.1162

Max Act: 0.6869. Min Act: -0.0000

Data Index: 445281 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 1.1162. Min Range: -1.1162

Max Act: 0.6126. Min Act: -0.0000

Data Index: 93182 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 1.1162. Min Range: -1.1162

Max Act: 0.5527. Min Act: -0.0000

Data Index: 542074 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 1.1162. Min Range: -1.1162

Max Act: 0.6202. Min Act: -0.0000

Data Index: 933229 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 1.1162. Min Range: -1.1162

Max Act: 0.5844. Min Act: -0.0000

Data Index: 425908 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 1.1162. Min Range: -1.1162

Max Act: 0.6275. Min Act: -0.0000

Data Index: 193068 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 1.1162. Min Range: -1.1162

Max Act: 0.5569. Min Act: -0.0000

Data Index: 873701 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 1.1162. Min Range: -1.1162

Max Act: 0.5938. Min Act: -0.0000

Data Index: 251051 (C4 (Web Text))

Max Activating Token Index: 240