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

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

Neuron 3907 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1259. Min Act: -0.0001

Data Index: 788657 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1113. Min Act: -0.0002

Data Index: 961537 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0917. Min Act: -0.0002

Data Index: 969818 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0797. Min Act: -0.0002

Data Index: 946878 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0899. Min Act: -0.0001

Data Index: 1305415 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0870. Min Act: -0.0002

Data Index: 1312884 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0906. Min Act: -0.0001

Data Index: 343123 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0877. Min Act: -0.0002

Data Index: 717373 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0853. Min Act: -0.0001

Data Index: 1118757 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0888. Min Act: -0.0002

Data Index: 1158647 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0793. Min Act: -0.0001

Data Index: 737770 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0848. Min Act: -0.0002

Data Index: 1191978 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0785. Min Act: -0.0002

Data Index: 438125 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0790. Min Act: -0.0001

Data Index: 81208 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0785. Min Act: -0.0002

Data Index: 1021609 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0809. Min Act: -0.0002

Data Index: 988876 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0747. Min Act: -0.0002

Data Index: 334025 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0821. Min Act: -0.0002

Data Index: 65522 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0780. Min Act: -0.0001

Data Index: 1368383 (Python Code)

Max Activating Token Index: 77

Text #19

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0832. Min Act: -0.0001

Data Index: 688565 (C4 (Web Text))

Max Activating Token Index: 367