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

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

Neuron 3735 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.4410. Min Act: -0.0000

Data Index: 656391 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.3815. Min Act: -0.0000

Data Index: 190361 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.3693. Min Act: -0.0000

Data Index: 25525 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.3506. Min Act: -0.0000

Data Index: 112792 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.3074. Min Act: -0.0000

Data Index: 721062 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.3191. Min Act: -0.0000

Data Index: 236064 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.3117. Min Act: -0.0000

Data Index: 28285 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.3051. Min Act: -0.0000

Data Index: 1086171 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.3081. Min Act: -0.0000

Data Index: 856234 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.3027. Min Act: -0.0000

Data Index: 643880 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.3119. Min Act: -0.0000

Data Index: 189024 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.2985. Min Act: -0.0000

Data Index: 1029737 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.2964. Min Act: -0.0000

Data Index: 792363 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.2968. Min Act: -0.0000

Data Index: 271188 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.3003. Min Act: -0.0000

Data Index: 1165941 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.3225. Min Act: -0.0000

Data Index: 789801 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.2912. Min Act: -0.0000

Data Index: 501982 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.2880. Min Act: -0.0000

Data Index: 184178 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.2824. Min Act: -0.0000

Data Index: 174746 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.2720. Min Act: -0.0000

Data Index: 518237 (C4 (Web Text))

Max Activating Token Index: 713