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

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

Neuron 3669 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0199. Min Range: -3.0199

Max Act: 3.0199. Min Act: -0.0000

Data Index: 628421 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 3.0199. Min Range: -3.0199

Max Act: 2.7310. Min Act: -0.0000

Data Index: 387823 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 3.0199. Min Range: -3.0199

Max Act: 2.3863. Min Act: -0.0000

Data Index: 269432 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 3.0199. Min Range: -3.0199

Max Act: 2.4986. Min Act: -0.0000

Data Index: 964848 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 3.0199. Min Range: -3.0199

Max Act: 2.2446. Min Act: -0.0000

Data Index: 450776 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 3.0199. Min Range: -3.0199

Max Act: 2.3596. Min Act: -0.0000

Data Index: 1133944 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 3.0199. Min Range: -3.0199

Max Act: 2.1974. Min Act: -0.0000

Data Index: 805820 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 3.0199. Min Range: -3.0199

Max Act: 1.9416. Min Act: -0.0000

Data Index: 390403 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 3.0199. Min Range: -3.0199

Max Act: 2.0525. Min Act: -0.0000

Data Index: 74498 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 3.0199. Min Range: -3.0199

Max Act: 2.2672. Min Act: -0.0000

Data Index: 775598 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 3.0199. Min Range: -3.0199

Max Act: 2.0371. Min Act: -0.0000

Data Index: 522988 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 3.0199. Min Range: -3.0199

Max Act: 2.1177. Min Act: -0.0000

Data Index: 96925 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 3.0199. Min Range: -3.0199

Max Act: 2.0442. Min Act: -0.0000

Data Index: 1207899 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 3.0199. Min Range: -3.0199

Max Act: 1.9031. Min Act: -0.0000

Data Index: 51651 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 3.0199. Min Range: -3.0199

Max Act: 1.9146. Min Act: -0.0000

Data Index: 594502 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 3.0199. Min Range: -3.0199

Max Act: 1.8964. Min Act: -0.0000

Data Index: 1359550 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 3.0199. Min Range: -3.0199

Max Act: 1.8800. Min Act: -0.0000

Data Index: 775823 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 3.0199. Min Range: -3.0199

Max Act: 1.9866. Min Act: -0.0000

Data Index: 100218 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 3.0199. Min Range: -3.0199

Max Act: 2.0827. Min Act: -0.0000

Data Index: 965009 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 3.0199. Min Range: -3.0199

Max Act: 2.0884. Min Act: -0.0000

Data Index: 1278607 (C4 (Web Text))

Max Activating Token Index: 746