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

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

Neuron 5827 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.8137. Min Act: -0.0000

Data Index: 712380 (C4 (Web Text))

Max Activating Token Index: 437

Text #1

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.7192. Min Act: -0.0000

Data Index: 709683 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.6644. Min Act: -0.0000

Data Index: 576218 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.5992. Min Act: -0.0000

Data Index: 67727 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.5430. Min Act: -0.0000

Data Index: 154769 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.5879. Min Act: -0.0000

Data Index: 277335 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.6018. Min Act: -0.0000

Data Index: 1273908 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.4844. Min Act: -0.0000

Data Index: 770762 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.5295. Min Act: -0.0000

Data Index: 328932 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.4611. Min Act: -0.0000

Data Index: 988405 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.4530. Min Act: -0.0000

Data Index: 1313658 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.4261. Min Act: -0.0000

Data Index: 1117118 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.4111. Min Act: -0.0000

Data Index: 125526 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.4033. Min Act: -0.0000

Data Index: 695708 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.4064. Min Act: -0.0000

Data Index: 266162 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.4284. Min Act: -0.0000

Data Index: 546633 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.3871. Min Act: -0.0000

Data Index: 628185 (C4 (Web Text))

Max Activating Token Index: 372

Text #17

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.3887. Min Act: -0.0000

Data Index: 328189 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.3953. Min Act: -0.0000

Data Index: 260593 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.3924. Min Act: -0.0000

Data Index: 903436 (C4 (Web Text))

Max Activating Token Index: 645