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

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

Neuron 4363 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: 0.4422. Min Range: -0.4422

Max Act: 0.4422. Min Act: -0.0000

Data Index: 1325841 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3864. Min Act: -0.0000

Data Index: 1259855 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3666. Min Act: -0.0000

Data Index: 949685 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3320. Min Act: -0.0000

Data Index: 724379 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3189. Min Act: -0.0000

Data Index: 543416 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.2933. Min Act: -0.0000

Data Index: 871857 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.2809. Min Act: -0.0000

Data Index: 573616 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.2921. Min Act: -0.0000

Data Index: 109171 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.2980. Min Act: -0.0000

Data Index: 1086702 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.2408. Min Act: -0.0000

Data Index: 756164 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.2767. Min Act: -0.0000

Data Index: 772211 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.2579. Min Act: -0.0000

Data Index: 622165 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.2752. Min Act: -0.0000

Data Index: 319523 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.2610. Min Act: -0.0000

Data Index: 1078480 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.2439. Min Act: -0.0000

Data Index: 1349289 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.2473. Min Act: -0.0000

Data Index: 1027603 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.2554. Min Act: -0.0000

Data Index: 570421 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.2548. Min Act: -0.0000

Data Index: 195429 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.2373. Min Act: -0.0000

Data Index: 1200916 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.2473. Min Act: -0.0000

Data Index: 1267170 (C4 (Web Text))

Max Activating Token Index: 597