Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 412 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.2214. Min Range: -3.2214

Max Act: 3.2214. Min Act: -0.0002

Data Index: 1333743 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 3.2214. Min Range: -3.2214

Max Act: 2.9485. Min Act: -0.0002

Data Index: 812861 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 3.2214. Min Range: -3.2214

Max Act: 2.9629. Min Act: -0.0002

Data Index: 1018077 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 3.2214. Min Range: -3.2214

Max Act: 3.1457. Min Act: -0.0002

Data Index: 511414 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 3.2214. Min Range: -3.2214

Max Act: 2.8250. Min Act: -0.0002

Data Index: 967925 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 3.2214. Min Range: -3.2214

Max Act: 2.9209. Min Act: -0.0002

Data Index: 1073577 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 3.2214. Min Range: -3.2214

Max Act: 2.8264. Min Act: -0.0002

Data Index: 678379 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 3.2214. Min Range: -3.2214

Max Act: 2.6973. Min Act: -0.0002

Data Index: 876401 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 3.2214. Min Range: -3.2214

Max Act: 2.6009. Min Act: -0.0002

Data Index: 1195711 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 3.2214. Min Range: -3.2214

Max Act: 2.6019. Min Act: -0.0002

Data Index: 980764 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 3.2214. Min Range: -3.2214

Max Act: 2.4005. Min Act: -0.0002

Data Index: 1298710 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 3.2214. Min Range: -3.2214

Max Act: 2.4457. Min Act: -0.0002

Data Index: 242395 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 3.2214. Min Range: -3.2214

Max Act: 2.4041. Min Act: -0.0002

Data Index: 336366 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 3.2214. Min Range: -3.2214

Max Act: 2.4779. Min Act: -0.0002

Data Index: 1015225 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 3.2214. Min Range: -3.2214

Max Act: 2.3332. Min Act: -0.0002

Data Index: 1286894 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 3.2214. Min Range: -3.2214

Max Act: 2.6409. Min Act: -0.0002

Data Index: 762664 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 3.2214. Min Range: -3.2214

Max Act: 2.2774. Min Act: -0.0002

Data Index: 69101 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 3.2214. Min Range: -3.2214

Max Act: 2.5003. Min Act: -0.0002

Data Index: 59577 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 3.2214. Min Range: -3.2214

Max Act: 2.4040. Min Act: -0.0002

Data Index: 433479 (C4 (Web Text))

Max Activating Token Index: 954

Text #19

Max Range: 3.2214. Min Range: -3.2214

Max Act: 2.3021. Min Act: -0.0002

Data Index: 1045006 (C4 (Web Text))

Max Activating Token Index: 669