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

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

Neuron 2832 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: 2.2312. Min Range: -2.2312

Max Act: 2.2312. Min Act: -0.0000

Data Index: 233998 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 2.2312. Min Range: -2.2312

Max Act: 2.2193. Min Act: -0.0000

Data Index: 886276 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 2.2312. Min Range: -2.2312

Max Act: 2.1851. Min Act: -0.0000

Data Index: 1217788 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 2.2312. Min Range: -2.2312

Max Act: 2.1927. Min Act: -0.0000

Data Index: 135974 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 2.2312. Min Range: -2.2312

Max Act: 2.1259. Min Act: -0.0000

Data Index: 912834 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 2.2312. Min Range: -2.2312

Max Act: 2.0920. Min Act: -0.0000

Data Index: 376202 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 2.2312. Min Range: -2.2312

Max Act: 2.0869. Min Act: -0.0000

Data Index: 799442 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 2.2312. Min Range: -2.2312

Max Act: 1.9456. Min Act: -0.0000

Data Index: 678280 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 2.2312. Min Range: -2.2312

Max Act: 2.0137. Min Act: -0.0000

Data Index: 925205 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 2.2312. Min Range: -2.2312

Max Act: 1.8985. Min Act: -0.0000

Data Index: 389658 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 2.2312. Min Range: -2.2312

Max Act: 1.9326. Min Act: -0.0000

Data Index: 185490 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 2.2312. Min Range: -2.2312

Max Act: 1.9738. Min Act: -0.0000

Data Index: 984017 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 2.2312. Min Range: -2.2312

Max Act: 1.8536. Min Act: -0.0000

Data Index: 799782 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 2.2312. Min Range: -2.2312

Max Act: 1.9470. Min Act: -0.0000

Data Index: 892483 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 2.2312. Min Range: -2.2312

Max Act: 2.0277. Min Act: -0.0000

Data Index: 250435 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 2.2312. Min Range: -2.2312

Max Act: 1.9145. Min Act: -0.0000

Data Index: 379626 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 2.2312. Min Range: -2.2312

Max Act: 1.9075. Min Act: -0.0000

Data Index: 269734 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 2.2312. Min Range: -2.2312

Max Act: 1.9069. Min Act: -0.0000

Data Index: 422240 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 2.2312. Min Range: -2.2312

Max Act: 1.9078. Min Act: -0.0000

Data Index: 300163 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 2.2312. Min Range: -2.2312

Max Act: 1.9883. Min Act: -0.0000

Data Index: 715577 (C4 (Web Text))

Max Activating Token Index: 186