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

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

Neuron 2001 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: 2.9480. Min Range: -2.9480

Max Act: 2.8035. Min Act: -0.0000

Data Index: 398957 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 2.9480. Min Range: -2.9480

Max Act: 2.9480. Min Act: -0.0000

Data Index: 655789 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 2.9480. Min Range: -2.9480

Max Act: 2.9221. Min Act: -0.0000

Data Index: 1346704 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 2.9480. Min Range: -2.9480

Max Act: 2.6075. Min Act: -0.0000

Data Index: 990197 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 2.9480. Min Range: -2.9480

Max Act: 2.8299. Min Act: -0.0000

Data Index: 35775 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 2.9480. Min Range: -2.9480

Max Act: 2.3525. Min Act: -0.0000

Data Index: 538235 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 2.9480. Min Range: -2.9480

Max Act: 2.4737. Min Act: -0.0000

Data Index: 1153236 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 2.9480. Min Range: -2.9480

Max Act: 2.5993. Min Act: -0.0000

Data Index: 1222932 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 2.9480. Min Range: -2.9480

Max Act: 2.5925. Min Act: -0.0000

Data Index: 777591 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 2.9480. Min Range: -2.9480

Max Act: 2.7924. Min Act: -0.0000

Data Index: 133354 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 2.9480. Min Range: -2.9480

Max Act: 2.5181. Min Act: -0.0000

Data Index: 1062444 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 2.9480. Min Range: -2.9480

Max Act: 2.4876. Min Act: -0.0000

Data Index: 1259950 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 2.9480. Min Range: -2.9480

Max Act: 2.5913. Min Act: -0.0000

Data Index: 438908 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 2.9480. Min Range: -2.9480

Max Act: 2.3212. Min Act: -0.0000

Data Index: 113446 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 2.9480. Min Range: -2.9480

Max Act: 2.1884. Min Act: -0.0000

Data Index: 382844 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 2.9480. Min Range: -2.9480

Max Act: 2.1975. Min Act: -0.0000

Data Index: 1305485 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 2.9480. Min Range: -2.9480

Max Act: 2.3113. Min Act: -0.0000

Data Index: 102316 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 2.9480. Min Range: -2.9480

Max Act: 2.4080. Min Act: -0.0000

Data Index: 682873 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 2.9480. Min Range: -2.9480

Max Act: 2.2855. Min Act: -0.0000

Data Index: 805294 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 2.9480. Min Range: -2.9480

Max Act: 2.3818. Min Act: -0.0000

Data Index: 776782 (C4 (Web Text))

Max Activating Token Index: 986