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

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

Neuron 6021 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3272. Min Range: -2.3272

Max Act: 2.3272. Min Act: -0.0000

Data Index: 409126 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 2.3272. Min Range: -2.3272

Max Act: 2.0776. Min Act: -0.0000

Data Index: 967314 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 2.3272. Min Range: -2.3272

Max Act: 1.6069. Min Act: 0.0000

Data Index: 972992 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 2.3272. Min Range: -2.3272

Max Act: 1.4975. Min Act: -0.0000

Data Index: 545800 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 2.3272. Min Range: -2.3272

Max Act: 1.3488. Min Act: -0.0000

Data Index: 666937 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 2.3272. Min Range: -2.3272

Max Act: 1.5205. Min Act: -0.0000

Data Index: 1354287 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 2.3272. Min Range: -2.3272

Max Act: 1.2874. Min Act: -0.0000

Data Index: 1089733 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 2.3272. Min Range: -2.3272

Max Act: 1.2984. Min Act: -0.0000

Data Index: 1005917 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 2.3272. Min Range: -2.3272

Max Act: 1.2834. Min Act: -0.0000

Data Index: 195223 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 2.3272. Min Range: -2.3272

Max Act: 1.3150. Min Act: -0.0000

Data Index: 842025 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 2.3272. Min Range: -2.3272

Max Act: 1.3054. Min Act: -0.0000

Data Index: 456031 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 2.3272. Min Range: -2.3272

Max Act: 1.2963. Min Act: -0.0000

Data Index: 1062795 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 2.3272. Min Range: -2.3272

Max Act: 1.4239. Min Act: -0.0000

Data Index: 272028 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 2.3272. Min Range: -2.3272

Max Act: 1.2502. Min Act: -0.0000

Data Index: 134768 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 2.3272. Min Range: -2.3272

Max Act: 1.2460. Min Act: -0.0000

Data Index: 178030 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 2.3272. Min Range: -2.3272

Max Act: 1.3254. Min Act: 0.0000

Data Index: 900108 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 2.3272. Min Range: -2.3272

Max Act: 1.2568. Min Act: -0.0000

Data Index: 1233088 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 2.3272. Min Range: -2.3272

Max Act: 1.1834. Min Act: -0.0000

Data Index: 918117 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 2.3272. Min Range: -2.3272

Max Act: 1.0524. Min Act: -0.0000

Data Index: 341298 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 2.3272. Min Range: -2.3272

Max Act: 1.1100. Min Act: -0.0000

Data Index: 786447 (C4 (Web Text))

Max Activating Token Index: 517