Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3840 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7921. Min Range: -1.7921

Max Act: 1.7921. Min Act: -0.0000

Data Index: 364863 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 1.7921. Min Range: -1.7921

Max Act: 1.6015. Min Act: -0.0000

Data Index: 107728 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 1.7921. Min Range: -1.7921

Max Act: 1.5553. Min Act: -0.0000

Data Index: 1209487 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 1.7921. Min Range: -1.7921

Max Act: 1.6180. Min Act: -0.0000

Data Index: 1104178 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 1.7921. Min Range: -1.7921

Max Act: 1.5667. Min Act: -0.0000

Data Index: 327472 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 1.7921. Min Range: -1.7921

Max Act: 1.5184. Min Act: -0.0000

Data Index: 1230562 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 1.7921. Min Range: -1.7921

Max Act: 1.4562. Min Act: -0.0000

Data Index: 1131211 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 1.7921. Min Range: -1.7921

Max Act: 1.3899. Min Act: -0.0000

Data Index: 905920 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 1.7921. Min Range: -1.7921

Max Act: 1.3423. Min Act: -0.0000

Data Index: 28802 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 1.7921. Min Range: -1.7921

Max Act: 1.4261. Min Act: -0.0000

Data Index: 447529 (C4 (Web Text))

Max Activating Token Index: 567

Text #10

Max Range: 1.7921. Min Range: -1.7921

Max Act: 1.3803. Min Act: -0.0000

Data Index: 581484 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 1.7921. Min Range: -1.7921

Max Act: 1.3341. Min Act: -0.0000

Data Index: 448081 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 1.7921. Min Range: -1.7921

Max Act: 1.3197. Min Act: -0.0000

Data Index: 993984 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 1.7921. Min Range: -1.7921

Max Act: 1.2957. Min Act: -0.0000

Data Index: 1064456 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 1.7921. Min Range: -1.7921

Max Act: 1.3749. Min Act: -0.0000

Data Index: 1175787 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 1.7921. Min Range: -1.7921

Max Act: 1.3006. Min Act: -0.0000

Data Index: 339410 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 1.7921. Min Range: -1.7921

Max Act: 1.3311. Min Act: -0.0000

Data Index: 977056 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 1.7921. Min Range: -1.7921

Max Act: 1.3610. Min Act: -0.0000

Data Index: 727879 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 1.7921. Min Range: -1.7921

Max Act: 1.2758. Min Act: -0.0000

Data Index: 768096 (C4 (Web Text))

Max Activating Token Index: 881

Text #19

Max Range: 1.7921. Min Range: -1.7921

Max Act: 1.3592. Min Act: -0.0000

Data Index: 1099028 (C4 (Web Text))

Max Activating Token Index: 28