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

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

Neuron 5871 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.7229. Min Range: -8.7229

Max Act: 8.7229. Min Act: -0.0000

Data Index: 861173 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 8.7229. Min Range: -8.7229

Max Act: 8.2969. Min Act: -0.0000

Data Index: 1216022 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 8.7229. Min Range: -8.7229

Max Act: 7.8964. Min Act: -0.0000

Data Index: 834107 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 8.7229. Min Range: -8.7229

Max Act: 6.8730. Min Act: -0.0000

Data Index: 1291974 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 8.7229. Min Range: -8.7229

Max Act: 6.9755. Min Act: -0.0000

Data Index: 875483 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 8.7229. Min Range: -8.7229

Max Act: 7.3030. Min Act: -0.0000

Data Index: 289310 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 8.7229. Min Range: -8.7229

Max Act: 7.1409. Min Act: -0.0000

Data Index: 409901 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 8.7229. Min Range: -8.7229

Max Act: 7.2510. Min Act: -0.0000

Data Index: 893619 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 8.7229. Min Range: -8.7229

Max Act: 7.2156. Min Act: -0.0000

Data Index: 1086235 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 8.7229. Min Range: -8.7229

Max Act: 6.7425. Min Act: -0.0000

Data Index: 583080 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 8.7229. Min Range: -8.7229

Max Act: 6.7529. Min Act: -0.0000

Data Index: 1188928 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 8.7229. Min Range: -8.7229

Max Act: 6.3387. Min Act: -0.0000

Data Index: 383790 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 8.7229. Min Range: -8.7229

Max Act: 6.7589. Min Act: -0.0000

Data Index: 285846 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 8.7229. Min Range: -8.7229

Max Act: 6.5439. Min Act: -0.0000

Data Index: 543294 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 8.7229. Min Range: -8.7229

Max Act: 6.3108. Min Act: -0.0000

Data Index: 52736 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 8.7229. Min Range: -8.7229

Max Act: 6.2200. Min Act: -0.0000

Data Index: 341681 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 8.7229. Min Range: -8.7229

Max Act: 6.1791. Min Act: -0.0000

Data Index: 653041 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 8.7229. Min Range: -8.7229

Max Act: 7.0871. Min Act: -0.0000

Data Index: 873456 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 8.7229. Min Range: -8.7229

Max Act: 6.2989. Min Act: -0.0000

Data Index: 548262 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 8.7229. Min Range: -8.7229

Max Act: 6.3072. Min Act: -0.0000

Data Index: 1270956 (C4 (Web Text))

Max Activating Token Index: 836