Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4647 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1795. Min Range: -1.1795

Max Act: 1.1795. Min Act: -0.0000

Data Index: 1172897 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 1.1795. Min Range: -1.1795

Max Act: 1.0377. Min Act: -0.0000

Data Index: 187202 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 1.1795. Min Range: -1.1795

Max Act: 0.9942. Min Act: -0.0000

Data Index: 513764 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 1.1795. Min Range: -1.1795

Max Act: 0.8671. Min Act: -0.0000

Data Index: 1245891 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 1.1795. Min Range: -1.1795

Max Act: 0.8394. Min Act: -0.0000

Data Index: 1316935 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 1.1795. Min Range: -1.1795

Max Act: 0.8066. Min Act: -0.0000

Data Index: 93295 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 1.1795. Min Range: -1.1795

Max Act: 0.7875. Min Act: -0.0000

Data Index: 1294252 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 1.1795. Min Range: -1.1795

Max Act: 0.8115. Min Act: -0.0000

Data Index: 1295921 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 1.1795. Min Range: -1.1795

Max Act: 0.7338. Min Act: -0.0000

Data Index: 220941 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 1.1795. Min Range: -1.1795

Max Act: 0.6989. Min Act: -0.0000

Data Index: 1301953 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 1.1795. Min Range: -1.1795

Max Act: 0.7580. Min Act: -0.0000

Data Index: 947481 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 1.1795. Min Range: -1.1795

Max Act: 0.7357. Min Act: -0.0000

Data Index: 491844 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 1.1795. Min Range: -1.1795

Max Act: 0.7362. Min Act: -0.0000

Data Index: 231732 (C4 (Web Text))

Max Activating Token Index: 423

Text #13

Max Range: 1.1795. Min Range: -1.1795

Max Act: 0.6986. Min Act: -0.0000

Data Index: 42809 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 1.1795. Min Range: -1.1795

Max Act: 0.7197. Min Act: -0.0000

Data Index: 1351428 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 1.1795. Min Range: -1.1795

Max Act: 0.6999. Min Act: -0.0000

Data Index: 1119398 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 1.1795. Min Range: -1.1795

Max Act: 0.6933. Min Act: -0.0000

Data Index: 948146 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 1.1795. Min Range: -1.1795

Max Act: 0.6983. Min Act: -0.0000

Data Index: 676745 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 1.1795. Min Range: -1.1795

Max Act: 0.6943. Min Act: -0.0000

Data Index: 498479 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 1.1795. Min Range: -1.1795

Max Act: 0.6291. Min Act: -0.0000

Data Index: 384139 (C4 (Web Text))

Max Activating Token Index: 65