Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 46 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2178. Min Range: -1.2178

Max Act: 1.1999. Min Act: -0.0001

Data Index: 793675 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 1.2178. Min Range: -1.2178

Max Act: 1.2178. Min Act: -0.0001

Data Index: 70293 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 1.2178. Min Range: -1.2178

Max Act: 1.0700. Min Act: -0.0001

Data Index: 100549 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 1.2178. Min Range: -1.2178

Max Act: 1.0749. Min Act: -0.0001

Data Index: 886153 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 1.2178. Min Range: -1.2178

Max Act: 1.0629. Min Act: -0.0001

Data Index: 226908 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 1.2178. Min Range: -1.2178

Max Act: 1.0704. Min Act: -0.0001

Data Index: 1091520 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 1.2178. Min Range: -1.2178

Max Act: 1.0453. Min Act: -0.0001

Data Index: 1250258 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 1.2178. Min Range: -1.2178

Max Act: 0.9436. Min Act: -0.0001

Data Index: 433948 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 1.2178. Min Range: -1.2178

Max Act: 1.0216. Min Act: -0.0001

Data Index: 1282106 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 1.2178. Min Range: -1.2178

Max Act: 0.9637. Min Act: -0.0001

Data Index: 1264095 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 1.2178. Min Range: -1.2178

Max Act: 0.9617. Min Act: -0.0001

Data Index: 217102 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 1.2178. Min Range: -1.2178

Max Act: 0.9525. Min Act: -0.0001

Data Index: 1233228 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 1.2178. Min Range: -1.2178

Max Act: 0.9876. Min Act: -0.0001

Data Index: 1012453 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 1.2178. Min Range: -1.2178

Max Act: 0.9777. Min Act: -0.0001

Data Index: 1344234 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 1.2178. Min Range: -1.2178

Max Act: 0.9734. Min Act: -0.0001

Data Index: 1183446 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 1.2178. Min Range: -1.2178

Max Act: 0.9918. Min Act: -0.0001

Data Index: 162493 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 1.2178. Min Range: -1.2178

Max Act: 0.9950. Min Act: -0.0001

Data Index: 203686 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 1.2178. Min Range: -1.2178

Max Act: 0.9537. Min Act: -0.0001

Data Index: 1170737 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 1.2178. Min Range: -1.2178

Max Act: 0.9558. Min Act: -0.0001

Data Index: 1306744 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 1.2178. Min Range: -1.2178

Max Act: 0.9451. Min Act: -0.0001

Data Index: 603518 (C4 (Web Text))

Max Activating Token Index: 166