Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1847 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1292. Min Act: -0.0003

Data Index: 1641725 (Python Code)

Max Activating Token Index: 2

Text #1

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1296. Min Act: -0.0003

Data Index: 994995 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1107. Min Act: -0.0003

Data Index: 262160 (C4 (Web Text))

Max Activating Token Index: 447

Text #3

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1033. Min Act: -0.0003

Data Index: 628607 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1019. Min Act: -0.0003

Data Index: 27797 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0997. Min Act: -0.0003

Data Index: 717737 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0969. Min Act: -0.0003

Data Index: 839498 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0974. Min Act: -0.0003

Data Index: 289163 (C4 (Web Text))

Max Activating Token Index: 370

Text #8

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0983. Min Act: -0.0003

Data Index: 1325620 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0970. Min Act: -0.0003

Data Index: 324005 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0937. Min Act: -0.0003

Data Index: 1257397 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0934. Min Act: -0.0003

Data Index: 89658 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0935. Min Act: -0.0003

Data Index: 1195068 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0949. Min Act: -0.0003

Data Index: 808988 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0952. Min Act: -0.0003

Data Index: 516851 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0949. Min Act: -0.0003

Data Index: 681447 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0914. Min Act: -0.0003

Data Index: 308319 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0895. Min Act: -0.0003

Data Index: 1297975 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0910. Min Act: -0.0003

Data Index: 1050069 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0914. Min Act: -0.0003

Data Index: 30203 (C4 (Web Text))

Max Activating Token Index: 852