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

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

Neuron 2513 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.8592. Min Act: -0.0000

Data Index: 1194134 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.6397. Min Act: -0.0001

Data Index: 628038 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.5199. Min Act: -0.0001

Data Index: 667261 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.5479. Min Act: -0.0001

Data Index: 487384 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.6302. Min Act: -0.0000

Data Index: 686862 (C4 (Web Text))

Max Activating Token Index: 328

Text #5

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.5225. Min Act: -0.0001

Data Index: 1244963 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.5251. Min Act: -0.0001

Data Index: 117387 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.6804. Min Act: -0.0001

Data Index: 34263 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.3392. Min Act: -0.0001

Data Index: 1219766 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.5448. Min Act: -0.0001

Data Index: 813584 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.3700. Min Act: -0.0001

Data Index: 1227892 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.5225. Min Act: -0.0001

Data Index: 5814 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.4370. Min Act: -0.0000

Data Index: 113650 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.4111. Min Act: -0.0001

Data Index: 1072844 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.3511. Min Act: -0.0001

Data Index: 545449 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.4148. Min Act: -0.0000

Data Index: 541768 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.3344. Min Act: -0.0001

Data Index: 302013 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.3188. Min Act: -0.0001

Data Index: 465394 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.3058. Min Act: -0.0001

Data Index: 420990 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.3150. Min Act: -0.0000

Data Index: 641930 (C4 (Web Text))

Max Activating Token Index: 664