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

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

Neuron 1503 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: 1.3199. Min Range: -1.3199

Max Act: 1.2474. Min Act: -0.0001

Data Index: 1160622 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 1.3199. Min Range: -1.3199

Max Act: 1.3199. Min Act: -0.0001

Data Index: 783283 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 1.3199. Min Range: -1.3199

Max Act: 1.0720. Min Act: -0.0001

Data Index: 1033508 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 1.3199. Min Range: -1.3199

Max Act: 1.0770. Min Act: -0.0001

Data Index: 681757 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 1.3199. Min Range: -1.3199

Max Act: 1.0615. Min Act: -0.0001

Data Index: 219134 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.9619. Min Act: -0.0001

Data Index: 460581 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.9755. Min Act: -0.0001

Data Index: 231552 (C4 (Web Text))

Max Activating Token Index: 604

Text #7

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.9269. Min Act: -0.0001

Data Index: 636754 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.9245. Min Act: -0.0001

Data Index: 1066224 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.8661. Min Act: -0.0001

Data Index: 67079 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.8885. Min Act: -0.0001

Data Index: 852455 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.8869. Min Act: -0.0001

Data Index: 949415 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.8661. Min Act: -0.0001

Data Index: 454061 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.8400. Min Act: -0.0001

Data Index: 886170 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.8053. Min Act: -0.0001

Data Index: 587181 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.8924. Min Act: -0.0001

Data Index: 472725 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.8326. Min Act: -0.0001

Data Index: 1042384 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.8583. Min Act: -0.0001

Data Index: 238354 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.8357. Min Act: -0.0001

Data Index: 647307 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.8299. Min Act: -0.0001

Data Index: 1185992 (C4 (Web Text))

Max Activating Token Index: 619