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

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

Neuron 1875 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0395. Min Range: -1.0395

Max Act: 1.0395. Min Act: -0.0001

Data Index: 196265 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.9340. Min Act: -0.0001

Data Index: 897493 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.8084. Min Act: -0.0001

Data Index: 727004 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.8849. Min Act: -0.0001

Data Index: 654532 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.9128. Min Act: -0.0001

Data Index: 1834 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.8679. Min Act: -0.0001

Data Index: 1073227 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.8852. Min Act: -0.0001

Data Index: 79716 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.8080. Min Act: -0.0001

Data Index: 1197747 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.8374. Min Act: -0.0001

Data Index: 545142 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.8682. Min Act: -0.0001

Data Index: 574311 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.9056. Min Act: -0.0001

Data Index: 844956 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.8723. Min Act: -0.0001

Data Index: 63617 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.7988. Min Act: -0.0001

Data Index: 1310622 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.8419. Min Act: -0.0001

Data Index: 469630 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.7796. Min Act: -0.0001

Data Index: 557573 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.6944. Min Act: -0.0001

Data Index: 143914 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.6977. Min Act: -0.0001

Data Index: 780893 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.7415. Min Act: -0.0001

Data Index: 200798 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.7510. Min Act: -0.0001

Data Index: 212991 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.7130. Min Act: -0.0001

Data Index: 1328224 (C4 (Web Text))

Max Activating Token Index: 170