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

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

Neuron 1134 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.9219. Min Act: -0.0000

Data Index: 199081 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.7893. Min Act: -0.0000

Data Index: 1221707 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.7438. Min Act: -0.0000

Data Index: 432580 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.6835. Min Act: -0.0000

Data Index: 995719 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.6877. Min Act: -0.0000

Data Index: 318024 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.6755. Min Act: -0.0001

Data Index: 1603071 (Python Code)

Max Activating Token Index: 80

Text #6

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.6319. Min Act: -0.0000

Data Index: 1332239 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.6457. Min Act: -0.0000

Data Index: 882445 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.6221. Min Act: -0.0000

Data Index: 1049982 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.6487. Min Act: -0.0000

Data Index: 1470798 (Python Code)

Max Activating Token Index: 630

Text #10

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.6498. Min Act: -0.0000

Data Index: 1202109 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.5884. Min Act: -0.0000

Data Index: 1243577 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.5671. Min Act: -0.0000

Data Index: 226900 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.6073. Min Act: -0.0000

Data Index: 776480 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.6537. Min Act: -0.0000

Data Index: 1136855 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.5742. Min Act: -0.0000

Data Index: 195376 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.5556. Min Act: -0.0000

Data Index: 1586340 (Python Code)

Max Activating Token Index: 972

Text #17

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.5694. Min Act: -0.0000

Data Index: 14513 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.5599. Min Act: -0.0000

Data Index: 1140537 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.5452. Min Act: -0.0000

Data Index: 515953 (C4 (Web Text))

Max Activating Token Index: 782