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

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

Neuron 3557 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3052. Min Range: -2.3052

Max Act: 2.3052. Min Act: -0.0001

Data Index: 1279396 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 2.3052. Min Range: -2.3052

Max Act: 1.5419. Min Act: -0.0001

Data Index: 609341 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 2.3052. Min Range: -2.3052

Max Act: 1.7130. Min Act: -0.0000

Data Index: 449624 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 2.3052. Min Range: -2.3052

Max Act: 1.6000. Min Act: -0.0001

Data Index: 1099690 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 2.3052. Min Range: -2.3052

Max Act: 1.6178. Min Act: -0.0000

Data Index: 1548796 (Python Code)

Max Activating Token Index: 462

Text #5

Max Range: 2.3052. Min Range: -2.3052

Max Act: 1.6017. Min Act: -0.0000

Data Index: 1016278 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 2.3052. Min Range: -2.3052

Max Act: 1.5255. Min Act: -0.0000

Data Index: 1074132 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 2.3052. Min Range: -2.3052

Max Act: 1.5235. Min Act: -0.0001

Data Index: 143397 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 2.3052. Min Range: -2.3052

Max Act: 1.4730. Min Act: -0.0001

Data Index: 422056 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 2.3052. Min Range: -2.3052

Max Act: 1.5030. Min Act: -0.0000

Data Index: 613908 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 2.3052. Min Range: -2.3052

Max Act: 1.4484. Min Act: -0.0001

Data Index: 1574012 (Python Code)

Max Activating Token Index: 680

Text #11

Max Range: 2.3052. Min Range: -2.3052

Max Act: 1.3885. Min Act: -0.0001

Data Index: 890754 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 2.3052. Min Range: -2.3052

Max Act: 1.3747. Min Act: -0.0000

Data Index: 1097911 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 2.3052. Min Range: -2.3052

Max Act: 1.4601. Min Act: -0.0001

Data Index: 333276 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 2.3052. Min Range: -2.3052

Max Act: 1.3248. Min Act: -0.0000

Data Index: 576326 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 2.3052. Min Range: -2.3052

Max Act: 1.4340. Min Act: -0.0000

Data Index: 1476090 (Python Code)

Max Activating Token Index: 142

Text #16

Max Range: 2.3052. Min Range: -2.3052

Max Act: 1.3855. Min Act: -0.0001

Data Index: 838136 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 2.3052. Min Range: -2.3052

Max Act: 1.2937. Min Act: -0.0001

Data Index: 753994 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 2.3052. Min Range: -2.3052

Max Act: 1.2902. Min Act: -0.0001

Data Index: 599372 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 2.3052. Min Range: -2.3052

Max Act: 1.2667. Min Act: -0.0000

Data Index: 1217877 (C4 (Web Text))

Max Activating Token Index: 759