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

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

Neuron 3424 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: 1.8951. Min Range: -1.8951

Max Act: 1.8951. Min Act: -0.0001

Data Index: 609724 (C4 (Web Text))

Max Activating Token Index: 269

Text #1

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.8300. Min Act: -0.0001

Data Index: 579915 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.6918. Min Act: -0.0001

Data Index: 311027 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.5137. Min Act: -0.0001

Data Index: 1320261 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.5372. Min Act: -0.0001

Data Index: 879777 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.5100. Min Act: -0.0001

Data Index: 648668 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.5318. Min Act: -0.0001

Data Index: 758706 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.5782. Min Act: -0.0001

Data Index: 977035 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.5010. Min Act: -0.0001

Data Index: 57418 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.4582. Min Act: -0.0001

Data Index: 67915 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.4590. Min Act: -0.0001

Data Index: 935477 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.5538. Min Act: -0.0001

Data Index: 459507 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.3410. Min Act: -0.0001

Data Index: 954614 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.4449. Min Act: -0.0001

Data Index: 557353 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.4682. Min Act: -0.0001

Data Index: 1005149 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.3204. Min Act: -0.0001

Data Index: 430015 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.3089. Min Act: -0.0001

Data Index: 543922 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.2966. Min Act: -0.0001

Data Index: 691768 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.3541. Min Act: -0.0001

Data Index: 329909 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.2827. Min Act: -0.0001

Data Index: 96907 (C4 (Web Text))

Max Activating Token Index: 658