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

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

Neuron 2977 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5643. Min Range: -1.5643

Max Act: 1.5643. Min Act: -0.0002

Data Index: 258412 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 1.5643. Min Range: -1.5643

Max Act: 1.4053. Min Act: -0.0002

Data Index: 681019 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 1.5643. Min Range: -1.5643

Max Act: 1.3903. Min Act: -0.0002

Data Index: 139764 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 1.5643. Min Range: -1.5643

Max Act: 1.3429. Min Act: -0.0002

Data Index: 187051 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 1.5643. Min Range: -1.5643

Max Act: 1.2320. Min Act: -0.0002

Data Index: 1315360 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 1.5643. Min Range: -1.5643

Max Act: 1.2330. Min Act: -0.0002

Data Index: 822974 (C4 (Web Text))

Max Activating Token Index: 602

Text #6

Max Range: 1.5643. Min Range: -1.5643

Max Act: 1.1747. Min Act: -0.0002

Data Index: 1053109 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 1.5643. Min Range: -1.5643

Max Act: 1.1761. Min Act: -0.0003

Data Index: 205371 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 1.5643. Min Range: -1.5643

Max Act: 1.0782. Min Act: -0.0002

Data Index: 1321053 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 1.5643. Min Range: -1.5643

Max Act: 1.0174. Min Act: -0.0002

Data Index: 1374665 (Python Code)

Max Activating Token Index: 80

Text #10

Max Range: 1.5643. Min Range: -1.5643

Max Act: 0.9965. Min Act: -0.0003

Data Index: 1058827 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 1.5643. Min Range: -1.5643

Max Act: 0.9920. Min Act: -0.0002

Data Index: 104375 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 1.5643. Min Range: -1.5643

Max Act: 0.9828. Min Act: -0.0002

Data Index: 1232912 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 1.5643. Min Range: -1.5643

Max Act: 0.9337. Min Act: -0.0002

Data Index: 1368373 (Python Code)

Max Activating Token Index: 82

Text #14

Max Range: 1.5643. Min Range: -1.5643

Max Act: 0.8977. Min Act: -0.0002

Data Index: 1368282 (Python Code)

Max Activating Token Index: 253

Text #15

Max Range: 1.5643. Min Range: -1.5643

Max Act: 0.9079. Min Act: -0.0002

Data Index: 811335 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 1.5643. Min Range: -1.5643

Max Act: 0.8898. Min Act: -0.0002

Data Index: 1625043 (Python Code)

Max Activating Token Index: 207

Text #17

Max Range: 1.5643. Min Range: -1.5643

Max Act: 0.8611. Min Act: -0.0002

Data Index: 1420019 (Python Code)

Max Activating Token Index: 13

Text #18

Max Range: 1.5643. Min Range: -1.5643

Max Act: 0.8789. Min Act: -0.0002

Data Index: 793731 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 1.5643. Min Range: -1.5643

Max Act: 0.8925. Min Act: -0.0002

Data Index: 1608022 (Python Code)

Max Activating Token Index: 237