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

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

Neuron 1538 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5726. Min Range: -3.5726

Max Act: 3.5726. Min Act: -0.0000

Data Index: 1333278 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 3.5726. Min Range: -3.5726

Max Act: 3.3141. Min Act: -0.0000

Data Index: 334190 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 3.5726. Min Range: -3.5726

Max Act: 3.2658. Min Act: -0.0000

Data Index: 309465 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 3.5726. Min Range: -3.5726

Max Act: 2.9417. Min Act: -0.0000

Data Index: 1212906 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 3.5726. Min Range: -3.5726

Max Act: 3.0536. Min Act: -0.0000

Data Index: 387240 (C4 (Web Text))

Max Activating Token Index: 328

Text #5

Max Range: 3.5726. Min Range: -3.5726

Max Act: 2.9436. Min Act: -0.0000

Data Index: 455418 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 3.5726. Min Range: -3.5726

Max Act: 2.8937. Min Act: -0.0000

Data Index: 1249983 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 3.5726. Min Range: -3.5726

Max Act: 2.8801. Min Act: -0.0000

Data Index: 837940 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 3.5726. Min Range: -3.5726

Max Act: 2.7478. Min Act: -0.0000

Data Index: 961129 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 3.5726. Min Range: -3.5726

Max Act: 2.5066. Min Act: -0.0000

Data Index: 996956 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 3.5726. Min Range: -3.5726

Max Act: 2.8600. Min Act: -0.0000

Data Index: 1315260 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 3.5726. Min Range: -3.5726

Max Act: 2.7038. Min Act: -0.0000

Data Index: 123041 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 3.5726. Min Range: -3.5726

Max Act: 2.9979. Min Act: -0.0000

Data Index: 1183881 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 3.5726. Min Range: -3.5726

Max Act: 2.5139. Min Act: -0.0000

Data Index: 1025399 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 3.5726. Min Range: -3.5726

Max Act: 2.4640. Min Act: -0.0000

Data Index: 1295699 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 3.5726. Min Range: -3.5726

Max Act: 2.6979. Min Act: -0.0000

Data Index: 481371 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 3.5726. Min Range: -3.5726

Max Act: 2.5740. Min Act: -0.0000

Data Index: 929095 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 3.5726. Min Range: -3.5726

Max Act: 2.4786. Min Act: -0.0000

Data Index: 217772 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 3.5726. Min Range: -3.5726

Max Act: 2.2216. Min Act: -0.0000

Data Index: 616620 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 3.5726. Min Range: -3.5726

Max Act: 2.5711. Min Act: -0.0000

Data Index: 47008 (C4 (Web Text))

Max Activating Token Index: 327