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

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

Neuron 2662 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.3089. Min Act: -0.0000

Data Index: 1181355 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2278. Min Act: -0.0000

Data Index: 127987 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2256. Min Act: -0.0000

Data Index: 299337 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2017. Min Act: -0.0000

Data Index: 1074153 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2059. Min Act: -0.0000

Data Index: 197397 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.1902. Min Act: -0.0000

Data Index: 60845 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.1989. Min Act: -0.0000

Data Index: 109782 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.1801. Min Act: -0.0000

Data Index: 702105 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.1934. Min Act: -0.0000

Data Index: 65715 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.1394. Min Act: -0.0000

Data Index: 545066 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.1487. Min Act: -0.0000

Data Index: 173485 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.1413. Min Act: -0.0000

Data Index: 1328398 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.1327. Min Act: -0.0000

Data Index: 964521 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.1232. Min Act: -0.0000

Data Index: 839111 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.1201. Min Act: -0.0000

Data Index: 493997 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.1264. Min Act: -0.0000

Data Index: 17554 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.1139. Min Act: -0.0000

Data Index: 208705 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.1127. Min Act: -0.0000

Data Index: 253381 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.1119. Min Act: -0.0000

Data Index: 25495 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.1088. Min Act: -0.0000

Data Index: 482925 (C4 (Web Text))

Max Activating Token Index: 934