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

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

Neuron 2440 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.8554. Min Act: -0.0001

Data Index: 1140284 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7475. Min Act: -0.0001

Data Index: 978798 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7391. Min Act: -0.0001

Data Index: 98137 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7098. Min Act: -0.0001

Data Index: 517942 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.6726. Min Act: -0.0001

Data Index: 438572 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.6400. Min Act: -0.0001

Data Index: 844683 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.6229. Min Act: -0.0001

Data Index: 994062 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.5752. Min Act: -0.0001

Data Index: 109360 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.5647. Min Act: -0.0001

Data Index: 785066 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.5899. Min Act: -0.0001

Data Index: 1107002 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.5884. Min Act: -0.0001

Data Index: 557615 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.5346. Min Act: -0.0001

Data Index: 628437 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.5911. Min Act: -0.0001

Data Index: 133349 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.5799. Min Act: -0.0001

Data Index: 509913 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.5090. Min Act: -0.0001

Data Index: 1349686 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.5043. Min Act: -0.0001

Data Index: 760969 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.5115. Min Act: -0.0001

Data Index: 14432 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.5076. Min Act: -0.0001

Data Index: 470788 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.5515. Min Act: -0.0001

Data Index: 1119600 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.5001. Min Act: -0.0001

Data Index: 63438 (C4 (Web Text))

Max Activating Token Index: 223