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

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

Neuron 4739 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.7297. Min Act: -0.0000

Data Index: 482631 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.6387. Min Act: -0.0000

Data Index: 1263805 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.4955. Min Act: -0.0000

Data Index: 623284 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.4706. Min Act: -0.0000

Data Index: 250971 (C4 (Web Text))

Max Activating Token Index: 587

Text #4

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.4852. Min Act: -0.0000

Data Index: 58717 (C4 (Web Text))

Max Activating Token Index: 609

Text #5

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.5233. Min Act: -0.0000

Data Index: 411222 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.5862. Min Act: -0.0000

Data Index: 1059132 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.5022. Min Act: -0.0000

Data Index: 409163 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.4064. Min Act: -0.0000

Data Index: 703966 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.3808. Min Act: -0.0000

Data Index: 839871 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.2804. Min Act: -0.0000

Data Index: 559563 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.3672. Min Act: -0.0000

Data Index: 986033 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.2858. Min Act: -0.0000

Data Index: 773447 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.2922. Min Act: -0.0000

Data Index: 197571 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.2785. Min Act: -0.0000

Data Index: 240154 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.2243. Min Act: -0.0000

Data Index: 1022609 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.2076. Min Act: -0.0000

Data Index: 77160 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.1216. Min Act: -0.0000

Data Index: 934759 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.2748. Min Act: -0.0000

Data Index: 119051 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 1.7297. Min Range: -1.7297

Max Act: 1.1534. Min Act: -0.0000

Data Index: 178025 (C4 (Web Text))

Max Activating Token Index: 241