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

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

Neuron 4230 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6086. Min Range: -3.6086

Max Act: 3.6086. Min Act: -0.0001

Data Index: 554762 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 3.6086. Min Range: -3.6086

Max Act: 3.5491. Min Act: -0.0000

Data Index: 1128100 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 3.6086. Min Range: -3.6086

Max Act: 3.2869. Min Act: -0.0001

Data Index: 788315 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 3.6086. Min Range: -3.6086

Max Act: 2.9954. Min Act: -0.0001

Data Index: 337268 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 3.6086. Min Range: -3.6086

Max Act: 3.3534. Min Act: -0.0001

Data Index: 580884 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 3.6086. Min Range: -3.6086

Max Act: 3.1212. Min Act: -0.0001

Data Index: 456780 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 3.6086. Min Range: -3.6086

Max Act: 3.0194. Min Act: -0.0001

Data Index: 1211689 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 3.6086. Min Range: -3.6086

Max Act: 2.9793. Min Act: -0.0001

Data Index: 699883 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 3.6086. Min Range: -3.6086

Max Act: 2.9270. Min Act: -0.0000

Data Index: 1086100 (C4 (Web Text))

Max Activating Token Index: 718

Text #9

Max Range: 3.6086. Min Range: -3.6086

Max Act: 2.8166. Min Act: -0.0000

Data Index: 289844 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 3.6086. Min Range: -3.6086

Max Act: 2.6822. Min Act: -0.0001

Data Index: 1142647 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 3.6086. Min Range: -3.6086

Max Act: 2.8613. Min Act: -0.0000

Data Index: 959980 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 3.6086. Min Range: -3.6086

Max Act: 2.7462. Min Act: -0.0000

Data Index: 50704 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 3.6086. Min Range: -3.6086

Max Act: 2.7446. Min Act: -0.0001

Data Index: 859880 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 3.6086. Min Range: -3.6086

Max Act: 3.0205. Min Act: -0.0001

Data Index: 1338668 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 3.6086. Min Range: -3.6086

Max Act: 2.7099. Min Act: -0.0001

Data Index: 102982 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 3.6086. Min Range: -3.6086

Max Act: 2.6748. Min Act: -0.0001

Data Index: 206681 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 3.6086. Min Range: -3.6086

Max Act: 2.6633. Min Act: -0.0000

Data Index: 481139 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 3.6086. Min Range: -3.6086

Max Act: 2.6305. Min Act: -0.0001

Data Index: 1035171 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 3.6086. Min Range: -3.6086

Max Act: 2.5133. Min Act: -0.0001

Data Index: 132752 (C4 (Web Text))

Max Activating Token Index: 12