Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2906 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2603. Min Act: -0.0003

Data Index: 184136 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2831. Min Act: -0.0003

Data Index: 1127901 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2739. Min Act: -0.0003

Data Index: 812518 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2760. Min Act: -0.0003

Data Index: 575128 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2535. Min Act: -0.0003

Data Index: 1072748 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2728. Min Act: -0.0003

Data Index: 1238414 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2353. Min Act: -0.0003

Data Index: 794772 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2701. Min Act: -0.0003

Data Index: 1041368 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2595. Min Act: -0.0003

Data Index: 525321 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2869. Min Act: -0.0003

Data Index: 1057007 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2567. Min Act: -0.0003

Data Index: 1160779 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2380. Min Act: -0.0003

Data Index: 248062 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.1804. Min Act: -0.0003

Data Index: 410316 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2436. Min Act: -0.0003

Data Index: 257730 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2411. Min Act: -0.0003

Data Index: 1251293 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2414. Min Act: -0.0003

Data Index: 938308 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2321. Min Act: -0.0003

Data Index: 906060 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2324. Min Act: -0.0003

Data Index: 318773 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2421. Min Act: -0.0003

Data Index: 457877 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2678. Min Act: -0.0003

Data Index: 863982 (C4 (Web Text))

Max Activating Token Index: 116