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

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

Neuron 335 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: 0.1464. Min Range: -0.1464

Max Act: 0.1432. Min Act: -0.0001

Data Index: 953168 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1464. Min Act: -0.0000

Data Index: 1144922 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1389. Min Act: -0.0001

Data Index: 993796 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1344. Min Act: -0.0001

Data Index: 1073439 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1313. Min Act: -0.0001

Data Index: 882184 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1348. Min Act: -0.0001

Data Index: 144945 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1248. Min Act: -0.0001

Data Index: 1279659 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1187. Min Act: -0.0001

Data Index: 451710 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1311. Min Act: -0.0001

Data Index: 693907 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1227. Min Act: -0.0001

Data Index: 424976 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1092. Min Act: -0.0001

Data Index: 102433 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1069. Min Act: -0.0001

Data Index: 285905 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1073. Min Act: -0.0001

Data Index: 592453 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.0997. Min Act: -0.0001

Data Index: 409281 (C4 (Web Text))

Max Activating Token Index: 430

Text #14

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.0964. Min Act: -0.0001

Data Index: 56423 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.0916. Min Act: -0.0000

Data Index: 1656291 (Python Code)

Max Activating Token Index: 247

Text #16

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.0928. Min Act: -0.0001

Data Index: 1345875 (C4 (Web Text))

Max Activating Token Index: 733

Text #17

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.0837. Min Act: -0.0001

Data Index: 370564 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.0921. Min Act: -0.0001

Data Index: 856122 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.0871. Min Act: -0.0001

Data Index: 1197090 (C4 (Web Text))

Max Activating Token Index: 979