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

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

Neuron 1039 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6635. Min Range: -2.6635

Max Act: 2.6635. Min Act: -0.0000

Data Index: 109970 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 2.6635. Min Range: -2.6635

Max Act: 2.4299. Min Act: -0.0000

Data Index: 1264528 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 2.6635. Min Range: -2.6635

Max Act: 1.9913. Min Act: -0.0000

Data Index: 787562 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 2.6635. Min Range: -2.6635

Max Act: 1.4842. Min Act: -0.0000

Data Index: 471575 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 2.6635. Min Range: -2.6635

Max Act: 1.3793. Min Act: -0.0000

Data Index: 1097096 (C4 (Web Text))

Max Activating Token Index: 605

Text #5

Max Range: 2.6635. Min Range: -2.6635

Max Act: 1.2482. Min Act: -0.0000

Data Index: 1145382 (C4 (Web Text))

Max Activating Token Index: 361

Text #6

Max Range: 2.6635. Min Range: -2.6635

Max Act: 1.3195. Min Act: -0.0000

Data Index: 285777 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 2.6635. Min Range: -2.6635

Max Act: 1.3045. Min Act: -0.0000

Data Index: 446507 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 2.6635. Min Range: -2.6635

Max Act: 1.2704. Min Act: -0.0000

Data Index: 1311168 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 2.6635. Min Range: -2.6635

Max Act: 1.2429. Min Act: -0.0000

Data Index: 409196 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 2.6635. Min Range: -2.6635

Max Act: 1.2114. Min Act: -0.0000

Data Index: 1084247 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 2.6635. Min Range: -2.6635

Max Act: 1.0927. Min Act: -0.0000

Data Index: 701861 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 2.6635. Min Range: -2.6635

Max Act: 1.1557. Min Act: -0.0000

Data Index: 890082 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 2.6635. Min Range: -2.6635

Max Act: 1.1525. Min Act: -0.0000

Data Index: 759590 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 2.6635. Min Range: -2.6635

Max Act: 1.1629. Min Act: -0.0000

Data Index: 168027 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 2.6635. Min Range: -2.6635

Max Act: 1.0781. Min Act: -0.0000

Data Index: 116816 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 2.6635. Min Range: -2.6635

Max Act: 1.0410. Min Act: -0.0000

Data Index: 541211 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 2.6635. Min Range: -2.6635

Max Act: 1.0936. Min Act: -0.0000

Data Index: 1282533 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 2.6635. Min Range: -2.6635

Max Act: 1.0894. Min Act: -0.0000

Data Index: 1205238 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 2.6635. Min Range: -2.6635

Max Act: 1.0243. Min Act: -0.0000

Data Index: 856830 (C4 (Web Text))

Max Activating Token Index: 14