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

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

Neuron 2820 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: 1.7804. Min Range: -1.7804

Max Act: 1.6521. Min Act: -0.0001

Data Index: 1011685 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.7804. Min Act: -0.0000

Data Index: 462814 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.6280. Min Act: -0.0000

Data Index: 406405 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.5591. Min Act: -0.0000

Data Index: 113697 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.6424. Min Act: -0.0000

Data Index: 133818 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.4981. Min Act: -0.0000

Data Index: 538015 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.6454. Min Act: -0.0000

Data Index: 1182216 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.5166. Min Act: -0.0000

Data Index: 553331 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.5472. Min Act: -0.0000

Data Index: 1086456 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.5750. Min Act: -0.0000

Data Index: 431336 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.4508. Min Act: -0.0000

Data Index: 1122258 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.4692. Min Act: -0.0000

Data Index: 77123 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.5935. Min Act: -0.0000

Data Index: 372797 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.5642. Min Act: -0.0001

Data Index: 1352398 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.5235. Min Act: -0.0000

Data Index: 869707 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.4812. Min Act: -0.0001

Data Index: 632701 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.4671. Min Act: -0.0000

Data Index: 195941 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.4599. Min Act: -0.0001

Data Index: 1192037 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.4520. Min Act: -0.0000

Data Index: 316232 (C4 (Web Text))

Max Activating Token Index: 548

Text #19

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.4289. Min Act: -0.0000

Data Index: 523790 (C4 (Web Text))

Max Activating Token Index: 760