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

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

Neuron 3142 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5604. Min Range: -3.5604

Max Act: 3.5604. Min Act: -0.0001

Data Index: 56782 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 3.5604. Min Range: -3.5604

Max Act: 2.8531. Min Act: -0.0001

Data Index: 1103310 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 3.5604. Min Range: -3.5604

Max Act: 2.6925. Min Act: -0.0001

Data Index: 1249219 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 3.5604. Min Range: -3.5604

Max Act: 2.9181. Min Act: -0.0001

Data Index: 1020654 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 3.5604. Min Range: -3.5604

Max Act: 3.0147. Min Act: -0.0001

Data Index: 947458 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 3.5604. Min Range: -3.5604

Max Act: 3.2791. Min Act: -0.0001

Data Index: 748502 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 3.5604. Min Range: -3.5604

Max Act: 3.0887. Min Act: -0.0001

Data Index: 1342877 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 3.5604. Min Range: -3.5604

Max Act: 2.9453. Min Act: -0.0001

Data Index: 906458 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 3.5604. Min Range: -3.5604

Max Act: 2.8081. Min Act: -0.0001

Data Index: 594690 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 3.5604. Min Range: -3.5604

Max Act: 2.8786. Min Act: -0.0001

Data Index: 1285292 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 3.5604. Min Range: -3.5604

Max Act: 2.7351. Min Act: -0.0001

Data Index: 1316305 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 3.5604. Min Range: -3.5604

Max Act: 2.7357. Min Act: -0.0001

Data Index: 456312 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 3.5604. Min Range: -3.5604

Max Act: 2.9354. Min Act: -0.0001

Data Index: 217591 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 3.5604. Min Range: -3.5604

Max Act: 2.6367. Min Act: -0.0001

Data Index: 1335926 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 3.5604. Min Range: -3.5604

Max Act: 2.7750. Min Act: -0.0001

Data Index: 356450 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 3.5604. Min Range: -3.5604

Max Act: 2.6520. Min Act: -0.0001

Data Index: 625654 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 3.5604. Min Range: -3.5604

Max Act: 2.7572. Min Act: -0.0001

Data Index: 96928 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 3.5604. Min Range: -3.5604

Max Act: 2.4581. Min Act: -0.0001

Data Index: 50541 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 3.5604. Min Range: -3.5604

Max Act: 2.4401. Min Act: -0.0001

Data Index: 924248 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 3.5604. Min Range: -3.5604

Max Act: 2.6610. Min Act: -0.0001

Data Index: 1223673 (C4 (Web Text))

Max Activating Token Index: 155