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

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

Neuron 4449 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4309. Min Range: -3.4309

Max Act: 3.4309. Min Act: -0.0000

Data Index: 635479 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.9685. Min Act: -0.0000

Data Index: 649466 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 3.4309. Min Range: -3.4309

Max Act: 3.0488. Min Act: -0.0000

Data Index: 53759 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.8267. Min Act: -0.0000

Data Index: 1265581 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.7819. Min Act: -0.0000

Data Index: 219362 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.7258. Min Act: -0.0000

Data Index: 948374 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.8525. Min Act: -0.0001

Data Index: 470174 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.7279. Min Act: -0.0000

Data Index: 1223306 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.9302. Min Act: -0.0000

Data Index: 91175 (C4 (Web Text))

Max Activating Token Index: 470

Text #9

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.8033. Min Act: -0.0000

Data Index: 888752 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.9007. Min Act: -0.0000

Data Index: 830018 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.7885. Min Act: -0.0000

Data Index: 17852 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.8994. Min Act: -0.0000

Data Index: 1237234 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.8863. Min Act: -0.0000

Data Index: 1090088 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.7563. Min Act: -0.0001

Data Index: 400177 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.8715. Min Act: -0.0000

Data Index: 855366 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.8512. Min Act: -0.0000

Data Index: 613947 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.7282. Min Act: -0.0000

Data Index: 1001965 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.5738. Min Act: -0.0000

Data Index: 1254389 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.6708. Min Act: -0.0000

Data Index: 435728 (C4 (Web Text))

Max Activating Token Index: 868