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

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

Neuron 3379 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.5526. Min Act: -0.0001

Data Index: 1118746 (C4 (Web Text))

Max Activating Token Index: 589

Text #1

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4848. Min Act: -0.0001

Data Index: 621557 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4631. Min Act: -0.0001

Data Index: 1104716 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4312. Min Act: -0.0001

Data Index: 657416 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4442. Min Act: -0.0001

Data Index: 552783 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4371. Min Act: -0.0001

Data Index: 333666 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4078. Min Act: -0.0001

Data Index: 284838 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.3980. Min Act: -0.0001

Data Index: 294935 (C4 (Web Text))

Max Activating Token Index: 345

Text #8

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4172. Min Act: -0.0001

Data Index: 230506 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.3964. Min Act: -0.0001

Data Index: 965785 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.3585. Min Act: -0.0001

Data Index: 682386 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.3685. Min Act: -0.0001

Data Index: 921559 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.3628. Min Act: -0.0001

Data Index: 871848 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.3536. Min Act: -0.0001

Data Index: 506062 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.3248. Min Act: -0.0001

Data Index: 947385 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.3084. Min Act: -0.0001

Data Index: 206296 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.2998. Min Act: -0.0001

Data Index: 461270 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.2840. Min Act: -0.0001

Data Index: 204688 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.2714. Min Act: -0.0001

Data Index: 432424 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.2965. Min Act: -0.0001

Data Index: 1088021 (C4 (Web Text))

Max Activating Token Index: 796