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

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

Neuron 3067 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8940. Min Range: -1.8940

Max Act: 1.8940. Min Act: -0.0000

Data Index: 716830 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 1.8940. Min Range: -1.8940

Max Act: 1.6986. Min Act: -0.0000

Data Index: 848346 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 1.8940. Min Range: -1.8940

Max Act: 1.6084. Min Act: -0.0000

Data Index: 1185677 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 1.8940. Min Range: -1.8940

Max Act: 1.5790. Min Act: -0.0000

Data Index: 888273 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 1.8940. Min Range: -1.8940

Max Act: 1.5591. Min Act: -0.0000

Data Index: 553946 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 1.8940. Min Range: -1.8940

Max Act: 1.5332. Min Act: -0.0000

Data Index: 375989 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 1.8940. Min Range: -1.8940

Max Act: 1.6275. Min Act: -0.0000

Data Index: 612730 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 1.8940. Min Range: -1.8940

Max Act: 1.5180. Min Act: -0.0000

Data Index: 889608 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 1.8940. Min Range: -1.8940

Max Act: 1.4881. Min Act: -0.0000

Data Index: 263083 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 1.8940. Min Range: -1.8940

Max Act: 1.4874. Min Act: -0.0000

Data Index: 1192592 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 1.8940. Min Range: -1.8940

Max Act: 1.5413. Min Act: -0.0000

Data Index: 1258101 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 1.8940. Min Range: -1.8940

Max Act: 1.4458. Min Act: -0.0000

Data Index: 793645 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 1.8940. Min Range: -1.8940

Max Act: 1.4132. Min Act: -0.0000

Data Index: 236319 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 1.8940. Min Range: -1.8940

Max Act: 1.3594. Min Act: -0.0000

Data Index: 863230 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 1.8940. Min Range: -1.8940

Max Act: 1.4714. Min Act: -0.0000

Data Index: 380805 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 1.8940. Min Range: -1.8940

Max Act: 1.3950. Min Act: -0.0000

Data Index: 488228 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 1.8940. Min Range: -1.8940

Max Act: 1.3758. Min Act: -0.0000

Data Index: 533645 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 1.8940. Min Range: -1.8940

Max Act: 1.3051. Min Act: -0.0000

Data Index: 376085 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 1.8940. Min Range: -1.8940

Max Act: 1.3727. Min Act: -0.0000

Data Index: 216826 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 1.8940. Min Range: -1.8940

Max Act: 1.3719. Min Act: -0.0000

Data Index: 1347109 (C4 (Web Text))

Max Activating Token Index: 417