Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3194 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.3307. Min Range: -3.3307

Max Act: 3.1914. Min Act: -0.0001

Data Index: 1244591 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 3.3307. Min Range: -3.3307

Max Act: 3.3307. Min Act: -0.0001

Data Index: 1144807 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 3.3307. Min Range: -3.3307

Max Act: 3.0130. Min Act: -0.0001

Data Index: 814986 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 3.3307. Min Range: -3.3307

Max Act: 3.1251. Min Act: -0.0001

Data Index: 1155412 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 3.3307. Min Range: -3.3307

Max Act: 3.0183. Min Act: -0.0001

Data Index: 816382 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 3.3307. Min Range: -3.3307

Max Act: 2.9788. Min Act: -0.0001

Data Index: 133222 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 3.3307. Min Range: -3.3307

Max Act: 2.9629. Min Act: -0.0001

Data Index: 412363 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 3.3307. Min Range: -3.3307

Max Act: 2.7572. Min Act: -0.0001

Data Index: 1156799 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 3.3307. Min Range: -3.3307

Max Act: 2.9929. Min Act: -0.0001

Data Index: 11696 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 3.3307. Min Range: -3.3307

Max Act: 2.8653. Min Act: -0.0001

Data Index: 1023506 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 3.3307. Min Range: -3.3307

Max Act: 2.7460. Min Act: -0.0001

Data Index: 1208280 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 3.3307. Min Range: -3.3307

Max Act: 2.7422. Min Act: -0.0001

Data Index: 217466 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 3.3307. Min Range: -3.3307

Max Act: 2.7086. Min Act: -0.0001

Data Index: 812892 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 3.3307. Min Range: -3.3307

Max Act: 2.6624. Min Act: -0.0001

Data Index: 1240300 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 3.3307. Min Range: -3.3307

Max Act: 2.6197. Min Act: -0.0001

Data Index: 1359836 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 3.3307. Min Range: -3.3307

Max Act: 2.7328. Min Act: -0.0001

Data Index: 398166 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 3.3307. Min Range: -3.3307

Max Act: 2.4393. Min Act: -0.0001

Data Index: 1129128 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 3.3307. Min Range: -3.3307

Max Act: 2.4807. Min Act: -0.0001

Data Index: 805597 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 3.3307. Min Range: -3.3307

Max Act: 2.5601. Min Act: -0.0001

Data Index: 61886 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 3.3307. Min Range: -3.3307

Max Act: 2.5431. Min Act: -0.0001

Data Index: 50183 (C4 (Web Text))

Max Activating Token Index: 756