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

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

Neuron 4946 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0587. Min Act: -0.0002

Data Index: 167584 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0511. Min Act: -0.0002

Data Index: 790447 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0498. Min Act: -0.0001

Data Index: 509241 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0480. Min Act: -0.0001

Data Index: 434724 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0469. Min Act: -0.0002

Data Index: 943591 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0463. Min Act: -0.0002

Data Index: 422026 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0469. Min Act: -0.0001

Data Index: 1340642 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0435. Min Act: -0.0001

Data Index: 721457 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0432. Min Act: -0.0001

Data Index: 292263 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0427. Min Act: -0.0002

Data Index: 142134 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1116799 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0422. Min Act: -0.0002

Data Index: 406403 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0422. Min Act: -0.0002

Data Index: 96261 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0423. Min Act: -0.0002

Data Index: 1264583 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0410. Min Act: -0.0002

Data Index: 1309866 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0401. Min Act: -0.0002

Data Index: 664399 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0408. Min Act: -0.0002

Data Index: 65022 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1150955 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0410. Min Act: -0.0002

Data Index: 1300949 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0391. Min Act: -0.0002

Data Index: 358290 (C4 (Web Text))

Max Activating Token Index: 576