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

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

Neuron 4073 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.9975. Min Act: -0.0002

Data Index: 1306328 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.9768. Min Act: -0.0002

Data Index: 580766 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.9353. Min Act: -0.0002

Data Index: 2809 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.9423. Min Act: -0.0002

Data Index: 1161335 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.9211. Min Act: -0.0002

Data Index: 509519 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.9193. Min Act: -0.0002

Data Index: 370432 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.9013. Min Act: -0.0002

Data Index: 398432 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.9008. Min Act: -0.0002

Data Index: 1203277 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.8612. Min Act: -0.0003

Data Index: 771263 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.8567. Min Act: -0.0002

Data Index: 936337 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.8772. Min Act: -0.0002

Data Index: 1175789 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.8727. Min Act: -0.0002

Data Index: 398640 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.8611. Min Act: -0.0002

Data Index: 983442 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.8677. Min Act: -0.0002

Data Index: 523032 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.8371. Min Act: -0.0002

Data Index: 420046 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.8378. Min Act: -0.0003

Data Index: 553861 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.8448. Min Act: -0.0002

Data Index: 1140039 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.8400. Min Act: -0.0002

Data Index: 81839 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.8483. Min Act: -0.0002

Data Index: 179162 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 0.9975. Min Range: -0.9975

Max Act: 0.8271. Min Act: -0.0002

Data Index: 1066861 (C4 (Web Text))

Max Activating Token Index: 595