Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1924 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.6208. Min Act: -0.0003

Data Index: 661715 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.6468. Min Act: -0.0003

Data Index: 433316 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5561. Min Act: -0.0003

Data Index: 807107 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5908. Min Act: -0.0003

Data Index: 362228 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.6119. Min Act: -0.0003

Data Index: 90074 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5199. Min Act: -0.0003

Data Index: 720476 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5925. Min Act: -0.0003

Data Index: 25857 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5016. Min Act: -0.0003

Data Index: 1181160 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5864. Min Act: -0.0003

Data Index: 1270902 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5026. Min Act: -0.0003

Data Index: 1131486 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5368. Min Act: -0.0003

Data Index: 1263364 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5674. Min Act: -0.0003

Data Index: 333491 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5532. Min Act: -0.0003

Data Index: 1002813 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5337. Min Act: -0.0003

Data Index: 349379 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5512. Min Act: -0.0003

Data Index: 878431 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5143. Min Act: -0.0003

Data Index: 364751 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.4950. Min Act: -0.0003

Data Index: 69721 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5406. Min Act: -0.0003

Data Index: 253375 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5074. Min Act: -0.0003

Data Index: 1331763 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5396. Min Act: -0.0003

Data Index: 1232180 (C4 (Web Text))

Max Activating Token Index: 23