Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1416 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3451. Min Range: -1.3451

Max Act: 1.3451. Min Act: -0.0001

Data Index: 594759 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 1.3451. Min Range: -1.3451

Max Act: 1.2339. Min Act: -0.0001

Data Index: 565179 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 1.3451. Min Range: -1.3451

Max Act: 1.0857. Min Act: -0.0001

Data Index: 818299 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 1.3451. Min Range: -1.3451

Max Act: 1.1559. Min Act: -0.0001

Data Index: 644662 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 1.3451. Min Range: -1.3451

Max Act: 1.1240. Min Act: -0.0001

Data Index: 1143280 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 1.3451. Min Range: -1.3451

Max Act: 1.1751. Min Act: -0.0001

Data Index: 116907 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 1.3451. Min Range: -1.3451

Max Act: 1.1314. Min Act: -0.0001

Data Index: 401784 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 1.3451. Min Range: -1.3451

Max Act: 1.1357. Min Act: -0.0001

Data Index: 456435 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 1.3451. Min Range: -1.3451

Max Act: 1.0560. Min Act: -0.0000

Data Index: 86875 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 1.3451. Min Range: -1.3451

Max Act: 0.9747. Min Act: -0.0001

Data Index: 242378 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 1.3451. Min Range: -1.3451

Max Act: 1.0024. Min Act: -0.0001

Data Index: 1309203 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 1.3451. Min Range: -1.3451

Max Act: 1.0372. Min Act: -0.0001

Data Index: 90560 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 1.3451. Min Range: -1.3451

Max Act: 1.0598. Min Act: -0.0000

Data Index: 398607 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 1.3451. Min Range: -1.3451

Max Act: 0.9860. Min Act: -0.0001

Data Index: 245394 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 1.3451. Min Range: -1.3451

Max Act: 1.0483. Min Act: -0.0001

Data Index: 949511 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 1.3451. Min Range: -1.3451

Max Act: 1.0381. Min Act: -0.0000

Data Index: 215922 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 1.3451. Min Range: -1.3451

Max Act: 0.9947. Min Act: -0.0001

Data Index: 157277 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 1.3451. Min Range: -1.3451

Max Act: 1.0217. Min Act: -0.0001

Data Index: 535873 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 1.3451. Min Range: -1.3451

Max Act: 0.9630. Min Act: -0.0001

Data Index: 1223235 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 1.3451. Min Range: -1.3451

Max Act: 0.9600. Min Act: -0.0001

Data Index: 681207 (C4 (Web Text))

Max Activating Token Index: 582