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

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

Neuron 5112 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.8729. Min Act: -0.0001

Data Index: 979038 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6779. Min Act: -0.0001

Data Index: 849549 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6286. Min Act: -0.0001

Data Index: 403994 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6955. Min Act: -0.0001

Data Index: 1100145 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6673. Min Act: -0.0001

Data Index: 1561497 (Python Code)

Max Activating Token Index: 341

Text #5

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6567. Min Act: -0.0001

Data Index: 994111 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6089. Min Act: -0.0001

Data Index: 40810 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.5991. Min Act: -0.0001

Data Index: 219709 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.5355. Min Act: -0.0001

Data Index: 532365 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6023. Min Act: -0.0001

Data Index: 639832 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.5235. Min Act: -0.0001

Data Index: 277361 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.5414. Min Act: -0.0001

Data Index: 40165 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.5200. Min Act: -0.0001

Data Index: 895731 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.5152. Min Act: -0.0001

Data Index: 1326891 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.5118. Min Act: -0.0001

Data Index: 523084 (C4 (Web Text))

Max Activating Token Index: 734

Text #15

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.5145. Min Act: -0.0001

Data Index: 1295220 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.5195. Min Act: -0.0001

Data Index: 816021 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.4598. Min Act: -0.0001

Data Index: 965222 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.5307. Min Act: -0.0001

Data Index: 122209 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.5112. Min Act: -0.0001

Data Index: 224273 (C4 (Web Text))

Max Activating Token Index: 727