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

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

Neuron 148 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: 2.8656. Min Range: -2.8656

Max Act: 2.8656. Min Act: -0.0000

Data Index: 199488 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 2.8656. Min Range: -2.8656

Max Act: 2.7494. Min Act: -0.0000

Data Index: 193831 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 2.8656. Min Range: -2.8656

Max Act: 2.5333. Min Act: -0.0000

Data Index: 374844 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 2.8656. Min Range: -2.8656

Max Act: 2.6356. Min Act: -0.0000

Data Index: 404720 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 2.8656. Min Range: -2.8656

Max Act: 2.7171. Min Act: -0.0000

Data Index: 601814 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 2.8656. Min Range: -2.8656

Max Act: 2.4249. Min Act: -0.0000

Data Index: 618301 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 2.8656. Min Range: -2.8656

Max Act: 2.3950. Min Act: -0.0000

Data Index: 869666 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 2.8656. Min Range: -2.8656

Max Act: 2.3431. Min Act: -0.0000

Data Index: 622838 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 2.8656. Min Range: -2.8656

Max Act: 2.4717. Min Act: -0.0000

Data Index: 257480 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 2.8656. Min Range: -2.8656

Max Act: 2.2739. Min Act: -0.0000

Data Index: 985620 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 2.8656. Min Range: -2.8656

Max Act: 2.2109. Min Act: -0.0000

Data Index: 826002 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 2.8656. Min Range: -2.8656

Max Act: 2.2596. Min Act: -0.0000

Data Index: 146266 (C4 (Web Text))

Max Activating Token Index: 993

Text #12

Max Range: 2.8656. Min Range: -2.8656

Max Act: 2.0199. Min Act: -0.0000

Data Index: 1278949 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 2.8656. Min Range: -2.8656

Max Act: 2.1212. Min Act: -0.0000

Data Index: 73764 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 2.8656. Min Range: -2.8656

Max Act: 2.0984. Min Act: -0.0000

Data Index: 446864 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 2.8656. Min Range: -2.8656

Max Act: 2.1015. Min Act: -0.0000

Data Index: 2327 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 2.8656. Min Range: -2.8656

Max Act: 2.0929. Min Act: -0.0000

Data Index: 413910 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 2.8656. Min Range: -2.8656

Max Act: 1.9512. Min Act: -0.0000

Data Index: 968594 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 2.8656. Min Range: -2.8656

Max Act: 1.9034. Min Act: -0.0000

Data Index: 506469 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 2.8656. Min Range: -2.8656

Max Act: 1.8905. Min Act: -0.0000

Data Index: 448144 (C4 (Web Text))

Max Activating Token Index: 242