Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2103 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.0197. Min Range: -2.0197

Max Act: 2.0197. Min Act: 0.0000

Data Index: 1580945 (Python Code)

Max Activating Token Index: 23

Text #1

Max Range: 2.0197. Min Range: -2.0197

Max Act: 1.8550. Min Act: 0.0001

Data Index: 1458022 (Python Code)

Max Activating Token Index: 36

Text #2

Max Range: 2.0197. Min Range: -2.0197

Max Act: 1.8204. Min Act: 0.0001

Data Index: 1389546 (Python Code)

Max Activating Token Index: 29

Text #3

Max Range: 2.0197. Min Range: -2.0197

Max Act: 1.6934. Min Act: -0.0000

Data Index: 1562307 (Python Code)

Max Activating Token Index: 259

Text #4

Max Range: 2.0197. Min Range: -2.0197

Max Act: 1.6163. Min Act: 0.0000

Data Index: 1576913 (Python Code)

Max Activating Token Index: 309

Text #5

Max Range: 2.0197. Min Range: -2.0197

Max Act: 1.7287. Min Act: -0.0000

Data Index: 1402818 (Python Code)

Max Activating Token Index: 124

Text #6

Max Range: 2.0197. Min Range: -2.0197

Max Act: 1.4743. Min Act: -0.0000

Data Index: 1636884 (Python Code)

Max Activating Token Index: 183

Text #7

Max Range: 2.0197. Min Range: -2.0197

Max Act: 1.3673. Min Act: 0.0001

Data Index: 1585254 (Python Code)

Max Activating Token Index: 13

Text #8

Max Range: 2.0197. Min Range: -2.0197

Max Act: 1.3286. Min Act: 0.0000

Data Index: 1375390 (Python Code)

Max Activating Token Index: 556

Text #9

Max Range: 2.0197. Min Range: -2.0197

Max Act: 1.3559. Min Act: 0.0001

Data Index: 1619383 (Python Code)

Max Activating Token Index: 11

Text #10

Max Range: 2.0197. Min Range: -2.0197

Max Act: 1.2536. Min Act: 0.0001

Data Index: 1446894 (Python Code)

Max Activating Token Index: 21

Text #11

Max Range: 2.0197. Min Range: -2.0197

Max Act: 1.2466. Min Act: 0.0001

Data Index: 1637447 (Python Code)

Max Activating Token Index: 70

Text #12

Max Range: 2.0197. Min Range: -2.0197

Max Act: 1.2467. Min Act: 0.0001

Data Index: 1520507 (Python Code)

Max Activating Token Index: 204

Text #13

Max Range: 2.0197. Min Range: -2.0197

Max Act: 1.3030. Min Act: 0.0001

Data Index: 1584675 (Python Code)

Max Activating Token Index: 78

Text #14

Max Range: 2.0197. Min Range: -2.0197

Max Act: 1.2126. Min Act: 0.0001

Data Index: 1382698 (Python Code)

Max Activating Token Index: 233

Text #15

Max Range: 2.0197. Min Range: -2.0197

Max Act: 1.2349. Min Act: -0.0000

Data Index: 1543172 (Python Code)

Max Activating Token Index: 675

Text #16

Max Range: 2.0197. Min Range: -2.0197

Max Act: 1.1967. Min Act: -0.0000

Data Index: 1408500 (Python Code)

Max Activating Token Index: 83

Text #17

Max Range: 2.0197. Min Range: -2.0197

Max Act: 1.2903. Min Act: 0.0000

Data Index: 1618979 (Python Code)

Max Activating Token Index: 729

Text #18

Max Range: 2.0197. Min Range: -2.0197

Max Act: 1.1445. Min Act: 0.0001

Data Index: 1632718 (Python Code)

Max Activating Token Index: 219

Text #19

Max Range: 2.0197. Min Range: -2.0197

Max Act: 1.2065. Min Act: 0.0000

Data Index: 1598307 (Python Code)

Max Activating Token Index: 159