Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3393 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1336. Min Range: -1.1336

Max Act: 1.0644. Min Act: -0.0000

Data Index: 42625 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 1.1336. Min Range: -1.1336

Max Act: 1.1336. Min Act: -0.0000

Data Index: 911890 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 1.1336. Min Range: -1.1336

Max Act: 1.0981. Min Act: -0.0000

Data Index: 499620 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 1.1336. Min Range: -1.1336

Max Act: 1.0279. Min Act: -0.0000

Data Index: 23716 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 1.1336. Min Range: -1.1336

Max Act: 0.9811. Min Act: -0.0000

Data Index: 1059604 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 1.1336. Min Range: -1.1336

Max Act: 0.9913. Min Act: -0.0000

Data Index: 1111212 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 1.1336. Min Range: -1.1336

Max Act: 0.9822. Min Act: -0.0001

Data Index: 1049306 (C4 (Web Text))

Max Activating Token Index: 681

Text #7

Max Range: 1.1336. Min Range: -1.1336

Max Act: 0.9399. Min Act: -0.0000

Data Index: 1138967 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 1.1336. Min Range: -1.1336

Max Act: 0.9746. Min Act: -0.0001

Data Index: 1317811 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 1.1336. Min Range: -1.1336

Max Act: 0.9353. Min Act: -0.0001

Data Index: 496580 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 1.1336. Min Range: -1.1336

Max Act: 0.9289. Min Act: -0.0000

Data Index: 890831 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 1.1336. Min Range: -1.1336

Max Act: 0.9066. Min Act: -0.0000

Data Index: 1150955 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 1.1336. Min Range: -1.1336

Max Act: 0.8965. Min Act: -0.0000

Data Index: 674614 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 1.1336. Min Range: -1.1336

Max Act: 0.8610. Min Act: -0.0000

Data Index: 1336493 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 1.1336. Min Range: -1.1336

Max Act: 0.8755. Min Act: -0.0000

Data Index: 1270216 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 1.1336. Min Range: -1.1336

Max Act: 0.9020. Min Act: -0.0000

Data Index: 818756 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 1.1336. Min Range: -1.1336

Max Act: 0.8745. Min Act: -0.0000

Data Index: 377986 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 1.1336. Min Range: -1.1336

Max Act: 0.8786. Min Act: -0.0000

Data Index: 764060 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 1.1336. Min Range: -1.1336

Max Act: 0.9045. Min Act: -0.0000

Data Index: 713204 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 1.1336. Min Range: -1.1336

Max Act: 0.8302. Min Act: -0.0000

Data Index: 773534 (C4 (Web Text))

Max Activating Token Index: 787