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

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

Neuron 3305 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.3272. Min Act: -0.0001

Data Index: 592325 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2968. Min Act: -0.0002

Data Index: 876179 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.3060. Min Act: -0.0001

Data Index: 1173956 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2936. Min Act: -0.0001

Data Index: 785888 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2662. Min Act: -0.0002

Data Index: 893777 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2943. Min Act: -0.0001

Data Index: 415414 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2804. Min Act: -0.0002

Data Index: 942104 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2735. Min Act: -0.0002

Data Index: 886442 (C4 (Web Text))

Max Activating Token Index: 884

Text #8

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2725. Min Act: -0.0001

Data Index: 1269361 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2675. Min Act: -0.0001

Data Index: 994220 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2950. Min Act: -0.0001

Data Index: 295000 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2847. Min Act: -0.0001

Data Index: 852137 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2641. Min Act: -0.0002

Data Index: 373458 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2820. Min Act: -0.0002

Data Index: 984929 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2661. Min Act: -0.0002

Data Index: 1283624 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2558. Min Act: -0.0002

Data Index: 587155 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2634. Min Act: -0.0002

Data Index: 864922 (C4 (Web Text))

Max Activating Token Index: 724

Text #17

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2625. Min Act: -0.0001

Data Index: 1022806 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2865. Min Act: -0.0002

Data Index: 474430 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2693. Min Act: -0.0002

Data Index: 229755 (C4 (Web Text))

Max Activating Token Index: 608