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

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

Neuron 1152 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.4922. Min Act: -0.0000

Data Index: 258877 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.4401. Min Act: -0.0000

Data Index: 796829 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3383. Min Act: -0.0000

Data Index: 971824 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3235. Min Act: -0.0000

Data Index: 1326868 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3330. Min Act: -0.0000

Data Index: 75807 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3209. Min Act: -0.0000

Data Index: 1329794 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3082. Min Act: -0.0000

Data Index: 356746 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3179. Min Act: -0.0000

Data Index: 81120 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.2971. Min Act: -0.0000

Data Index: 270752 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3055. Min Act: -0.0000

Data Index: 510237 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3047. Min Act: -0.0000

Data Index: 160981 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.2905. Min Act: -0.0000

Data Index: 555256 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.2966. Min Act: -0.0000

Data Index: 330273 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.2920. Min Act: -0.0000

Data Index: 831894 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.2918. Min Act: -0.0000

Data Index: 203690 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.2812. Min Act: -0.0000

Data Index: 1253952 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.2815. Min Act: -0.0000

Data Index: 715117 (C4 (Web Text))

Max Activating Token Index: 311

Text #17

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.2893. Min Act: -0.0000

Data Index: 774826 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3080. Min Act: -0.0000

Data Index: 649897 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.2574. Min Act: -0.0000

Data Index: 566856 (C4 (Web Text))

Max Activating Token Index: 706