Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2415 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.7094. Min Act: -0.0003

Data Index: 1056414 (C4 (Web Text))

Max Activating Token Index: 371

Text #1

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.7202. Min Act: -0.0003

Data Index: 451328 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.7097. Min Act: -0.0003

Data Index: 1240089 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.7293. Min Act: -0.0003

Data Index: 932000 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.7253. Min Act: -0.0003

Data Index: 825763 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.6992. Min Act: -0.0003

Data Index: 7789 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.6330. Min Act: -0.0003

Data Index: 954178 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.6188. Min Act: -0.0003

Data Index: 864371 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.7059. Min Act: -0.0003

Data Index: 516848 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.6780. Min Act: -0.0003

Data Index: 612008 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.6403. Min Act: -0.0003

Data Index: 1121137 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.6569. Min Act: -0.0003

Data Index: 857656 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.6513. Min Act: -0.0003

Data Index: 614189 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.6638. Min Act: -0.0003

Data Index: 1298499 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.6598. Min Act: -0.0003

Data Index: 813746 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.6536. Min Act: -0.0003

Data Index: 160598 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.6032. Min Act: -0.0003

Data Index: 1334631 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.6652. Min Act: -0.0003

Data Index: 242119 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.6636. Min Act: -0.0003

Data Index: 108178 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.6344. Min Act: -0.0003

Data Index: 1282629 (C4 (Web Text))

Max Activating Token Index: 91