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

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

Neuron 2855 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8835. Min Range: -2.8835

Max Act: 2.8835. Min Act: -0.0001

Data Index: 199546 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 2.8835. Min Range: -2.8835

Max Act: 2.6119. Min Act: -0.0000

Data Index: 614578 (C4 (Web Text))

Max Activating Token Index: 737

Text #2

Max Range: 2.8835. Min Range: -2.8835

Max Act: 2.5190. Min Act: -0.0001

Data Index: 112686 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 2.8835. Min Range: -2.8835

Max Act: 2.5234. Min Act: -0.0001

Data Index: 412871 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 2.8835. Min Range: -2.8835

Max Act: 2.4745. Min Act: -0.0000

Data Index: 926441 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 2.8835. Min Range: -2.8835

Max Act: 2.3855. Min Act: -0.0000

Data Index: 1308024 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 2.8835. Min Range: -2.8835

Max Act: 2.4982. Min Act: -0.0000

Data Index: 1227079 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 2.8835. Min Range: -2.8835

Max Act: 2.2874. Min Act: -0.0001

Data Index: 1160009 (C4 (Web Text))

Max Activating Token Index: 666

Text #8

Max Range: 2.8835. Min Range: -2.8835

Max Act: 2.3411. Min Act: -0.0000

Data Index: 896138 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 2.8835. Min Range: -2.8835

Max Act: 2.3445. Min Act: -0.0000

Data Index: 319582 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 2.8835. Min Range: -2.8835

Max Act: 2.2696. Min Act: -0.0000

Data Index: 975581 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 2.8835. Min Range: -2.8835

Max Act: 2.2709. Min Act: -0.0000

Data Index: 469780 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 2.8835. Min Range: -2.8835

Max Act: 2.2981. Min Act: -0.0000

Data Index: 568883 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 2.8835. Min Range: -2.8835

Max Act: 2.2344. Min Act: -0.0001

Data Index: 1333970 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 2.8835. Min Range: -2.8835

Max Act: 2.1117. Min Act: -0.0001

Data Index: 121411 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 2.8835. Min Range: -2.8835

Max Act: 2.2203. Min Act: -0.0001

Data Index: 58489 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 2.8835. Min Range: -2.8835

Max Act: 2.2220. Min Act: -0.0001

Data Index: 32764 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 2.8835. Min Range: -2.8835

Max Act: 2.0726. Min Act: -0.0001

Data Index: 812216 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 2.8835. Min Range: -2.8835

Max Act: 2.0750. Min Act: -0.0000

Data Index: 229105 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 2.8835. Min Range: -2.8835

Max Act: 2.0468. Min Act: -0.0000

Data Index: 606810 (C4 (Web Text))

Max Activating Token Index: 6