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

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

Neuron 2702 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4947. Min Range: -5.4947

Max Act: 5.4947. Min Act: -0.0000

Data Index: 674180 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 5.4947. Min Range: -5.4947

Max Act: 5.0905. Min Act: -0.0000

Data Index: 987721 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 5.4947. Min Range: -5.4947

Max Act: 4.8932. Min Act: -0.0000

Data Index: 1156949 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 5.4947. Min Range: -5.4947

Max Act: 4.8743. Min Act: -0.0000

Data Index: 782645 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 5.4947. Min Range: -5.4947

Max Act: 4.7559. Min Act: -0.0000

Data Index: 572976 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 5.4947. Min Range: -5.4947

Max Act: 4.1368. Min Act: -0.0000

Data Index: 183145 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 5.4947. Min Range: -5.4947

Max Act: 4.0578. Min Act: -0.0000

Data Index: 1098529 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 5.4947. Min Range: -5.4947

Max Act: 4.1395. Min Act: -0.0000

Data Index: 100022 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 5.4947. Min Range: -5.4947

Max Act: 4.1262. Min Act: -0.0000

Data Index: 1205419 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 5.4947. Min Range: -5.4947

Max Act: 3.9388. Min Act: -0.0000

Data Index: 1074924 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 5.4947. Min Range: -5.4947

Max Act: 3.9479. Min Act: -0.0000

Data Index: 525525 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 5.4947. Min Range: -5.4947

Max Act: 3.4246. Min Act: -0.0000

Data Index: 906680 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 5.4947. Min Range: -5.4947

Max Act: 3.5047. Min Act: -0.0000

Data Index: 881973 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 5.4947. Min Range: -5.4947

Max Act: 3.4808. Min Act: -0.0000

Data Index: 128189 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 5.4947. Min Range: -5.4947

Max Act: 3.4344. Min Act: -0.0000

Data Index: 1105466 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 5.4947. Min Range: -5.4947

Max Act: 3.3874. Min Act: -0.0000

Data Index: 569985 (C4 (Web Text))

Max Activating Token Index: 1008

Text #16

Max Range: 5.4947. Min Range: -5.4947

Max Act: 3.2227. Min Act: -0.0000

Data Index: 842218 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 5.4947. Min Range: -5.4947

Max Act: 3.3591. Min Act: -0.0000

Data Index: 458457 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 5.4947. Min Range: -5.4947

Max Act: 3.0766. Min Act: -0.0000

Data Index: 1158368 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 5.4947. Min Range: -5.4947

Max Act: 3.2367. Min Act: -0.0000

Data Index: 264678 (C4 (Web Text))

Max Activating Token Index: 249