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

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

Neuron 3191 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.6771. Min Act: -0.0001

Data Index: 803895 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5619. Min Act: -0.0001

Data Index: 664235 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.4942. Min Act: -0.0001

Data Index: 16849 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.4419. Min Act: -0.0001

Data Index: 1201734 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.3976. Min Act: -0.0001

Data Index: 869744 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.3896. Min Act: -0.0001

Data Index: 410427 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.3565. Min Act: -0.0001

Data Index: 1071466 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.3831. Min Act: -0.0001

Data Index: 962372 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.3815. Min Act: -0.0001

Data Index: 172429 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.3737. Min Act: -0.0001

Data Index: 259712 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.3648. Min Act: -0.0001

Data Index: 835988 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.3600. Min Act: -0.0001

Data Index: 1074302 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.3154. Min Act: -0.0001

Data Index: 705492 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.2625. Min Act: -0.0001

Data Index: 1332637 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.3017. Min Act: -0.0001

Data Index: 13452 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.2940. Min Act: -0.0001

Data Index: 122823 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.3328. Min Act: -0.0001

Data Index: 121209 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.3201. Min Act: -0.0001

Data Index: 1268364 (C4 (Web Text))

Max Activating Token Index: 563

Text #18

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.3005. Min Act: -0.0001

Data Index: 457639 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.2619. Min Act: -0.0001

Data Index: 1001897 (C4 (Web Text))

Max Activating Token Index: 223