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

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

Neuron 1452 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1126. Min Range: -3.1126

Max Act: 3.0941. Min Act: -0.0000

Data Index: 686168 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 3.1126. Min Range: -3.1126

Max Act: 3.1126. Min Act: -0.0000

Data Index: 350030 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.8174. Min Act: -0.0000

Data Index: 499775 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.3976. Min Act: -0.0000

Data Index: 398000 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.6506. Min Act: -0.0000

Data Index: 80347 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.8619. Min Act: -0.0000

Data Index: 1149428 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.5356. Min Act: -0.0000

Data Index: 1217141 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.5403. Min Act: -0.0000

Data Index: 292169 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.5912. Min Act: -0.0000

Data Index: 536419 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.5929. Min Act: -0.0000

Data Index: 974575 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.4489. Min Act: -0.0000

Data Index: 37187 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.6215. Min Act: -0.0000

Data Index: 537216 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.2712. Min Act: -0.0000

Data Index: 962707 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.4391. Min Act: -0.0000

Data Index: 146206 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.4415. Min Act: -0.0000

Data Index: 60475 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.5641. Min Act: -0.0000

Data Index: 193778 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.1561. Min Act: -0.0000

Data Index: 155818 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.3767. Min Act: -0.0000

Data Index: 393871 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.4898. Min Act: -0.0000

Data Index: 397525 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.2175. Min Act: -0.0000

Data Index: 510643 (C4 (Web Text))

Max Activating Token Index: 874