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

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

Neuron 4020 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8775. Min Range: -0.8775

Max Act: 0.8775. Min Act: -0.0000

Data Index: 191276 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 0.8775. Min Range: -0.8775

Max Act: 0.8072. Min Act: -0.0000

Data Index: 450743 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 0.8775. Min Range: -0.8775

Max Act: 0.7350. Min Act: -0.0000

Data Index: 1137243 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 0.8775. Min Range: -0.8775

Max Act: 0.7104. Min Act: -0.0000

Data Index: 346727 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 0.8775. Min Range: -0.8775

Max Act: 0.6984. Min Act: -0.0000

Data Index: 616495 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 0.8775. Min Range: -0.8775

Max Act: 0.6820. Min Act: -0.0000

Data Index: 617482 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 0.8775. Min Range: -0.8775

Max Act: 0.6715. Min Act: -0.0001

Data Index: 834665 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 0.8775. Min Range: -0.8775

Max Act: 0.6245. Min Act: -0.0001

Data Index: 792419 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 0.8775. Min Range: -0.8775

Max Act: 0.6707. Min Act: -0.0000

Data Index: 79488 (C4 (Web Text))

Max Activating Token Index: 1010

Text #9

Max Range: 0.8775. Min Range: -0.8775

Max Act: 0.6327. Min Act: -0.0000

Data Index: 71162 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 0.8775. Min Range: -0.8775

Max Act: 0.6282. Min Act: -0.0000

Data Index: 227217 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 0.8775. Min Range: -0.8775

Max Act: 0.6086. Min Act: -0.0000

Data Index: 1127206 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 0.8775. Min Range: -0.8775

Max Act: 0.6299. Min Act: -0.0000

Data Index: 296978 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 0.8775. Min Range: -0.8775

Max Act: 0.6258. Min Act: -0.0000

Data Index: 978020 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 0.8775. Min Range: -0.8775

Max Act: 0.5977. Min Act: -0.0000

Data Index: 1284989 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 0.8775. Min Range: -0.8775

Max Act: 0.5872. Min Act: -0.0000

Data Index: 635810 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 0.8775. Min Range: -0.8775

Max Act: 0.5992. Min Act: -0.0000

Data Index: 1310759 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 0.8775. Min Range: -0.8775

Max Act: 0.5770. Min Act: -0.0001

Data Index: 978412 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 0.8775. Min Range: -0.8775

Max Act: 0.5757. Min Act: -0.0001

Data Index: 171676 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 0.8775. Min Range: -0.8775

Max Act: 0.5927. Min Act: -0.0000

Data Index: 34983 (C4 (Web Text))

Max Activating Token Index: 772