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

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

Neuron 442 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: 0.7991. Min Range: -0.7991

Max Act: 0.7991. Min Act: -0.0003

Data Index: 724978 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.6075. Min Act: -0.0003

Data Index: 244778 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.6058. Min Act: -0.0003

Data Index: 2735 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.6188. Min Act: -0.0003

Data Index: 469200 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.5363. Min Act: -0.0003

Data Index: 421315 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.5803. Min Act: -0.0003

Data Index: 1028423 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.5735. Min Act: -0.0003

Data Index: 908197 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.5704. Min Act: -0.0003

Data Index: 349678 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.5059. Min Act: -0.0003

Data Index: 1117369 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.5385. Min Act: -0.0003

Data Index: 1083520 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.5049. Min Act: -0.0003

Data Index: 741301 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.5160. Min Act: -0.0003

Data Index: 26102 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.5540. Min Act: -0.0003

Data Index: 1262154 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.5094. Min Act: -0.0003

Data Index: 442578 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.4983. Min Act: -0.0003

Data Index: 1300473 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.5040. Min Act: -0.0003

Data Index: 360153 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.5127. Min Act: -0.0003

Data Index: 842923 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.5562. Min Act: -0.0003

Data Index: 952405 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.5006. Min Act: -0.0003

Data Index: 1056240 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.4765. Min Act: -0.0003

Data Index: 285363 (C4 (Web Text))

Max Activating Token Index: 388