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

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

Neuron 602 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.4968. Min Act: -0.0001

Data Index: 880408 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.3780. Min Act: -0.0001

Data Index: 1199898 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.3804. Min Act: -0.0001

Data Index: 832141 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.3456. Min Act: -0.0001

Data Index: 1047152 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.3487. Min Act: -0.0001

Data Index: 251494 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.3416. Min Act: -0.0001

Data Index: 62373 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.2958. Min Act: -0.0001

Data Index: 1009854 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.3197. Min Act: -0.0001

Data Index: 450557 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.3201. Min Act: -0.0001

Data Index: 1095307 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.3262. Min Act: -0.0000

Data Index: 674145 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.2968. Min Act: -0.0001

Data Index: 572308 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.2557. Min Act: -0.0001

Data Index: 554874 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.2847. Min Act: -0.0001

Data Index: 969756 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.3053. Min Act: -0.0001

Data Index: 988342 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.2804. Min Act: -0.0001

Data Index: 551568 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.2770. Min Act: -0.0001

Data Index: 1176236 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.2898. Min Act: -0.0001

Data Index: 960553 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.2915. Min Act: -0.0001

Data Index: 962838 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.2698. Min Act: -0.0001

Data Index: 455074 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.2882. Min Act: -0.0001

Data Index: 74991 (C4 (Web Text))

Max Activating Token Index: 685