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

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

Neuron 2853 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0370. Min Range: -2.0370

Max Act: 2.0370. Min Act: -0.0000

Data Index: 1353531 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 2.0370. Min Range: -2.0370

Max Act: 1.4324. Min Act: -0.0000

Data Index: 335792 (C4 (Web Text))

Max Activating Token Index: 995

Text #2

Max Range: 2.0370. Min Range: -2.0370

Max Act: 1.4298. Min Act: -0.0000

Data Index: 833011 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 2.0370. Min Range: -2.0370

Max Act: 1.4337. Min Act: -0.0000

Data Index: 1354892 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 2.0370. Min Range: -2.0370

Max Act: 1.4141. Min Act: -0.0000

Data Index: 1157467 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 2.0370. Min Range: -2.0370

Max Act: 1.3063. Min Act: -0.0000

Data Index: 841117 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 2.0370. Min Range: -2.0370

Max Act: 1.2784. Min Act: -0.0000

Data Index: 797409 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 2.0370. Min Range: -2.0370

Max Act: 1.3449. Min Act: -0.0000

Data Index: 68663 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 2.0370. Min Range: -2.0370

Max Act: 1.3085. Min Act: -0.0000

Data Index: 1245365 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 2.0370. Min Range: -2.0370

Max Act: 1.3339. Min Act: -0.0000

Data Index: 1293988 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 2.0370. Min Range: -2.0370

Max Act: 1.3256. Min Act: -0.0000

Data Index: 481745 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 2.0370. Min Range: -2.0370

Max Act: 1.2937. Min Act: -0.0000

Data Index: 1074517 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 2.0370. Min Range: -2.0370

Max Act: 1.2161. Min Act: -0.0000

Data Index: 1344899 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 2.0370. Min Range: -2.0370

Max Act: 1.2871. Min Act: -0.0000

Data Index: 1299214 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 2.0370. Min Range: -2.0370

Max Act: 1.1841. Min Act: -0.0000

Data Index: 472137 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 2.0370. Min Range: -2.0370

Max Act: 1.1515. Min Act: -0.0000

Data Index: 1247292 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 2.0370. Min Range: -2.0370

Max Act: 1.1168. Min Act: -0.0000

Data Index: 1337837 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 2.0370. Min Range: -2.0370

Max Act: 1.1859. Min Act: -0.0000

Data Index: 287441 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 2.0370. Min Range: -2.0370

Max Act: 1.0529. Min Act: -0.0000

Data Index: 1051527 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 2.0370. Min Range: -2.0370

Max Act: 0.9842. Min Act: -0.0000

Data Index: 668991 (C4 (Web Text))

Max Activating Token Index: 278