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

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

Neuron 4902 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: 1.7646. Min Range: -1.7646

Max Act: 1.7646. Min Act: -0.0001

Data Index: 697799 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.4798. Min Act: -0.0001

Data Index: 696887 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.5140. Min Act: -0.0001

Data Index: 482409 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.4983. Min Act: -0.0001

Data Index: 603438 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.4596. Min Act: -0.0001

Data Index: 756892 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.3021. Min Act: -0.0001

Data Index: 510466 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.4085. Min Act: -0.0001

Data Index: 819914 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.2351. Min Act: -0.0001

Data Index: 832027 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.2344. Min Act: -0.0001

Data Index: 509073 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.2389. Min Act: -0.0001

Data Index: 1074153 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.1324. Min Act: -0.0001

Data Index: 858359 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.1941. Min Act: -0.0000

Data Index: 781384 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.2210. Min Act: -0.0001

Data Index: 589551 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.2032. Min Act: -0.0001

Data Index: 1042920 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.1596. Min Act: -0.0001

Data Index: 889623 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.2191. Min Act: -0.0001

Data Index: 682470 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.1047. Min Act: -0.0001

Data Index: 547756 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.0926. Min Act: -0.0000

Data Index: 260370 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.1166. Min Act: -0.0000

Data Index: 1011600 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 1.7646. Min Range: -1.7646

Max Act: 1.1015. Min Act: -0.0001

Data Index: 789668 (C4 (Web Text))

Max Activating Token Index: 798