Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5126 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.4085. Min Act: -0.0000

Data Index: 1260328 (C4 (Web Text))

Max Activating Token Index: 347

Text #1

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.4540. Min Act: -0.0000

Data Index: 1312866 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.3663. Min Act: -0.0000

Data Index: 1337856 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.2931. Min Act: -0.0000

Data Index: 287250 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.3125. Min Act: -0.0000

Data Index: 939044 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.2949. Min Act: -0.0000

Data Index: 1068798 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.2922. Min Act: -0.0000

Data Index: 813130 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.3004. Min Act: -0.0000

Data Index: 304530 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.2909. Min Act: -0.0000

Data Index: 750668 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.2821. Min Act: -0.0000

Data Index: 95636 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.2827. Min Act: -0.0000

Data Index: 65940 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.2749. Min Act: -0.0000

Data Index: 655928 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.2761. Min Act: -0.0000

Data Index: 574100 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.2546. Min Act: -0.0000

Data Index: 31446 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.2287. Min Act: -0.0000

Data Index: 625523 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.2661. Min Act: -0.0000

Data Index: 403380 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.2796. Min Act: -0.0000

Data Index: 278632 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.2557. Min Act: -0.0000

Data Index: 650145 (C4 (Web Text))

Max Activating Token Index: 543

Text #18

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.2584. Min Act: -0.0000

Data Index: 730380 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.2585. Min Act: -0.0000

Data Index: 191758 (C4 (Web Text))

Max Activating Token Index: 475