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

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

Neuron 352 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.4139. Min Act: -0.0002

Data Index: 566352 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3383. Min Act: -0.0002

Data Index: 787756 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3354. Min Act: -0.0002

Data Index: 993065 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3418. Min Act: -0.0002

Data Index: 1249861 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3245. Min Act: -0.0002

Data Index: 403315 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3312. Min Act: -0.0002

Data Index: 115285 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.2843. Min Act: -0.0002

Data Index: 435001 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3262. Min Act: -0.0002

Data Index: 233528 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3017. Min Act: -0.0002

Data Index: 270372 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3103. Min Act: -0.0002

Data Index: 669283 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3673. Min Act: -0.0002

Data Index: 1188742 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.2558. Min Act: -0.0002

Data Index: 1108582 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.2693. Min Act: -0.0002

Data Index: 462604 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3049. Min Act: -0.0002

Data Index: 247817 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3011. Min Act: -0.0002

Data Index: 908170 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3055. Min Act: -0.0002

Data Index: 1254612 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.2710. Min Act: -0.0002

Data Index: 457796 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3007. Min Act: -0.0002

Data Index: 1127653 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3013. Min Act: -0.0002

Data Index: 869054 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3415. Min Act: -0.0002

Data Index: 829344 (C4 (Web Text))

Max Activating Token Index: 63