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

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

Neuron 183 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8289. Min Range: -1.8289

Max Act: 1.8289. Min Act: -0.0001

Data Index: 905930 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 1.8289. Min Range: -1.8289

Max Act: 1.4845. Min Act: -0.0001

Data Index: 312686 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 1.8289. Min Range: -1.8289

Max Act: 1.4302. Min Act: -0.0001

Data Index: 480254 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 1.8289. Min Range: -1.8289

Max Act: 1.5002. Min Act: -0.0001

Data Index: 154843 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 1.8289. Min Range: -1.8289

Max Act: 1.4931. Min Act: -0.0001

Data Index: 807863 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 1.8289. Min Range: -1.8289

Max Act: 1.2993. Min Act: -0.0001

Data Index: 1179239 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 1.8289. Min Range: -1.8289

Max Act: 1.3745. Min Act: -0.0001

Data Index: 1308788 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 1.8289. Min Range: -1.8289

Max Act: 1.3647. Min Act: -0.0001

Data Index: 201603 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 1.8289. Min Range: -1.8289

Max Act: 1.3167. Min Act: -0.0001

Data Index: 1164613 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 1.8289. Min Range: -1.8289

Max Act: 1.2925. Min Act: -0.0001

Data Index: 538540 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 1.8289. Min Range: -1.8289

Max Act: 1.2528. Min Act: -0.0001

Data Index: 871357 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 1.8289. Min Range: -1.8289

Max Act: 1.3081. Min Act: -0.0001

Data Index: 1209948 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 1.8289. Min Range: -1.8289

Max Act: 1.2381. Min Act: -0.0001

Data Index: 940952 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 1.8289. Min Range: -1.8289

Max Act: 1.2286. Min Act: -0.0001

Data Index: 868921 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 1.8289. Min Range: -1.8289

Max Act: 1.2988. Min Act: -0.0001

Data Index: 824056 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 1.8289. Min Range: -1.8289

Max Act: 1.2042. Min Act: -0.0001

Data Index: 1129459 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 1.8289. Min Range: -1.8289

Max Act: 1.2344. Min Act: -0.0001

Data Index: 251370 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 1.8289. Min Range: -1.8289

Max Act: 1.2290. Min Act: -0.0001

Data Index: 696626 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 1.8289. Min Range: -1.8289

Max Act: 1.1794. Min Act: -0.0001

Data Index: 381921 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 1.8289. Min Range: -1.8289

Max Act: 1.1831. Min Act: -0.0001

Data Index: 1014337 (C4 (Web Text))

Max Activating Token Index: 963