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

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

Neuron 3103 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2317. Min Range: -1.2317

Max Act: 1.2317. Min Act: -0.0001

Data Index: 1547022 (Python Code)

Max Activating Token Index: 812

Text #1

Max Range: 1.2317. Min Range: -1.2317

Max Act: 1.1418. Min Act: -0.0001

Data Index: 1434802 (Python Code)

Max Activating Token Index: 388

Text #2

Max Range: 1.2317. Min Range: -1.2317

Max Act: 1.0672. Min Act: -0.0001

Data Index: 1362255 (Python Code)

Max Activating Token Index: 534

Text #3

Max Range: 1.2317. Min Range: -1.2317

Max Act: 1.0275. Min Act: -0.0001

Data Index: 1378544 (Python Code)

Max Activating Token Index: 446

Text #4

Max Range: 1.2317. Min Range: -1.2317

Max Act: 0.9998. Min Act: -0.0001

Data Index: 1545115 (Python Code)

Max Activating Token Index: 520

Text #5

Max Range: 1.2317. Min Range: -1.2317

Max Act: 1.0566. Min Act: -0.0001

Data Index: 1434980 (Python Code)

Max Activating Token Index: 194

Text #6

Max Range: 1.2317. Min Range: -1.2317

Max Act: 1.0157. Min Act: -0.0001

Data Index: 1368219 (Python Code)

Max Activating Token Index: 277

Text #7

Max Range: 1.2317. Min Range: -1.2317

Max Act: 0.9540. Min Act: -0.0001

Data Index: 1420294 (Python Code)

Max Activating Token Index: 92

Text #8

Max Range: 1.2317. Min Range: -1.2317

Max Act: 0.9284. Min Act: -0.0001

Data Index: 1627359 (Python Code)

Max Activating Token Index: 359

Text #9

Max Range: 1.2317. Min Range: -1.2317

Max Act: 0.9709. Min Act: -0.0001

Data Index: 1457397 (Python Code)

Max Activating Token Index: 139

Text #10

Max Range: 1.2317. Min Range: -1.2317

Max Act: 0.8786. Min Act: -0.0001

Data Index: 1448770 (Python Code)

Max Activating Token Index: 30

Text #11

Max Range: 1.2317. Min Range: -1.2317

Max Act: 0.8129. Min Act: -0.0001

Data Index: 1540183 (Python Code)

Max Activating Token Index: 245

Text #12

Max Range: 1.2317. Min Range: -1.2317

Max Act: 0.8636. Min Act: -0.0001

Data Index: 1526109 (Python Code)

Max Activating Token Index: 237

Text #13

Max Range: 1.2317. Min Range: -1.2317

Max Act: 0.9161. Min Act: -0.0001

Data Index: 1416712 (Python Code)

Max Activating Token Index: 297

Text #14

Max Range: 1.2317. Min Range: -1.2317

Max Act: 0.8142. Min Act: -0.0001

Data Index: 1382524 (Python Code)

Max Activating Token Index: 195

Text #15

Max Range: 1.2317. Min Range: -1.2317

Max Act: 0.8036. Min Act: -0.0001

Data Index: 1496129 (Python Code)

Max Activating Token Index: 186

Text #16

Max Range: 1.2317. Min Range: -1.2317

Max Act: 0.7629. Min Act: -0.0001

Data Index: 1629081 (Python Code)

Max Activating Token Index: 90

Text #17

Max Range: 1.2317. Min Range: -1.2317

Max Act: 0.8468. Min Act: -0.0001

Data Index: 1397498 (Python Code)

Max Activating Token Index: 30

Text #18

Max Range: 1.2317. Min Range: -1.2317

Max Act: 0.8330. Min Act: -0.0001

Data Index: 1650285 (Python Code)

Max Activating Token Index: 260

Text #19

Max Range: 1.2317. Min Range: -1.2317

Max Act: 0.8073. Min Act: -0.0001

Data Index: 1394444 (Python Code)

Max Activating Token Index: 218