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

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

Neuron 4524 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4129. Min Range: -1.4129

Max Act: 1.4129. Min Act: -0.0001

Data Index: 164785 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 1.4129. Min Range: -1.4129

Max Act: 1.3350. Min Act: -0.0001

Data Index: 41227 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 1.4129. Min Range: -1.4129

Max Act: 1.2744. Min Act: -0.0001

Data Index: 897383 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 1.4129. Min Range: -1.4129

Max Act: 1.2928. Min Act: -0.0001

Data Index: 866327 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 1.4129. Min Range: -1.4129

Max Act: 1.2494. Min Act: -0.0001

Data Index: 194816 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 1.4129. Min Range: -1.4129

Max Act: 1.2651. Min Act: -0.0001

Data Index: 11106 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 1.4129. Min Range: -1.4129

Max Act: 1.2124. Min Act: -0.0001

Data Index: 358573 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 1.4129. Min Range: -1.4129

Max Act: 1.1256. Min Act: -0.0001

Data Index: 1075383 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 1.4129. Min Range: -1.4129

Max Act: 1.0033. Min Act: -0.0001

Data Index: 1101482 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 1.4129. Min Range: -1.4129

Max Act: 1.0341. Min Act: -0.0001

Data Index: 618295 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 1.4129. Min Range: -1.4129

Max Act: 1.0837. Min Act: -0.0001

Data Index: 410487 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 1.4129. Min Range: -1.4129

Max Act: 1.0988. Min Act: -0.0001

Data Index: 830605 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 1.4129. Min Range: -1.4129

Max Act: 1.1038. Min Act: -0.0001

Data Index: 58296 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 1.4129. Min Range: -1.4129

Max Act: 1.0907. Min Act: -0.0001

Data Index: 13140 (C4 (Web Text))

Max Activating Token Index: 233

Text #14

Max Range: 1.4129. Min Range: -1.4129

Max Act: 1.0667. Min Act: -0.0001

Data Index: 356224 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 1.4129. Min Range: -1.4129

Max Act: 1.1086. Min Act: -0.0001

Data Index: 384872 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 1.4129. Min Range: -1.4129

Max Act: 1.0472. Min Act: -0.0001

Data Index: 293193 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 1.4129. Min Range: -1.4129

Max Act: 1.0569. Min Act: -0.0001

Data Index: 241404 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 1.4129. Min Range: -1.4129

Max Act: 1.1057. Min Act: -0.0001

Data Index: 618722 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 1.4129. Min Range: -1.4129

Max Act: 1.0431. Min Act: -0.0001

Data Index: 1040946 (C4 (Web Text))

Max Activating Token Index: 9