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

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

Neuron 4155 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3062. Min Range: -1.3062

Max Act: 1.2709. Min Act: -0.0000

Data Index: 101721 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 1.3062. Min Range: -1.3062

Max Act: 1.3062. Min Act: -0.0000

Data Index: 490461 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 1.3062. Min Range: -1.3062

Max Act: 1.2320. Min Act: -0.0000

Data Index: 121035 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 1.3062. Min Range: -1.3062

Max Act: 1.2605. Min Act: -0.0000

Data Index: 1572034 (Python Code)

Max Activating Token Index: 455

Text #4

Max Range: 1.3062. Min Range: -1.3062

Max Act: 1.2540. Min Act: -0.0000

Data Index: 1492349 (Python Code)

Max Activating Token Index: 78

Text #5

Max Range: 1.3062. Min Range: -1.3062

Max Act: 1.2064. Min Act: -0.0000

Data Index: 1451935 (Python Code)

Max Activating Token Index: 426

Text #6

Max Range: 1.3062. Min Range: -1.3062

Max Act: 1.1326. Min Act: -0.0000

Data Index: 1577429 (Python Code)

Max Activating Token Index: 131

Text #7

Max Range: 1.3062. Min Range: -1.3062

Max Act: 1.2274. Min Act: -0.0000

Data Index: 239272 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 1.3062. Min Range: -1.3062

Max Act: 1.1206. Min Act: -0.0000

Data Index: 937934 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 1.3062. Min Range: -1.3062

Max Act: 1.1160. Min Act: -0.0000

Data Index: 185874 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 1.3062. Min Range: -1.3062

Max Act: 1.1070. Min Act: -0.0000

Data Index: 467989 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 1.3062. Min Range: -1.3062

Max Act: 1.1130. Min Act: -0.0000

Data Index: 315380 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 1.3062. Min Range: -1.3062

Max Act: 1.1081. Min Act: -0.0000

Data Index: 1349150 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 1.3062. Min Range: -1.3062

Max Act: 1.0880. Min Act: -0.0000

Data Index: 1510886 (Python Code)

Max Activating Token Index: 322

Text #14

Max Range: 1.3062. Min Range: -1.3062

Max Act: 1.0927. Min Act: -0.0000

Data Index: 60511 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 1.3062. Min Range: -1.3062

Max Act: 1.1540. Min Act: -0.0000

Data Index: 16382 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 1.3062. Min Range: -1.3062

Max Act: 1.0851. Min Act: -0.0000

Data Index: 24700 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 1.3062. Min Range: -1.3062

Max Act: 1.0698. Min Act: 0.0001

Data Index: 528808 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 1.3062. Min Range: -1.3062

Max Act: 1.0402. Min Act: -0.0000

Data Index: 1465771 (Python Code)

Max Activating Token Index: 117

Text #19

Max Range: 1.3062. Min Range: -1.3062

Max Act: 1.0692. Min Act: -0.0000

Data Index: 1605272 (Python Code)

Max Activating Token Index: 433