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

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

Neuron 4137 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5979. Min Range: -3.5979

Max Act: 3.5979. Min Act: -0.0000

Data Index: 763070 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 3.5979. Min Range: -3.5979

Max Act: 3.2068. Min Act: -0.0000

Data Index: 607939 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 3.5979. Min Range: -3.5979

Max Act: 3.2088. Min Act: -0.0000

Data Index: 983477 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 3.5979. Min Range: -3.5979

Max Act: 2.9170. Min Act: -0.0000

Data Index: 1008661 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 3.5979. Min Range: -3.5979

Max Act: 2.8803. Min Act: -0.0000

Data Index: 533770 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 3.5979. Min Range: -3.5979

Max Act: 2.8955. Min Act: -0.0000

Data Index: 538697 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 3.5979. Min Range: -3.5979

Max Act: 2.9198. Min Act: -0.0000

Data Index: 920059 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 3.5979. Min Range: -3.5979

Max Act: 2.9091. Min Act: -0.0000

Data Index: 290951 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 3.5979. Min Range: -3.5979

Max Act: 2.5301. Min Act: -0.0000

Data Index: 1166179 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 3.5979. Min Range: -3.5979

Max Act: 2.7637. Min Act: -0.0000

Data Index: 1228754 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 3.5979. Min Range: -3.5979

Max Act: 2.6879. Min Act: -0.0000

Data Index: 576199 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 3.5979. Min Range: -3.5979

Max Act: 2.6726. Min Act: -0.0000

Data Index: 1320606 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 3.5979. Min Range: -3.5979

Max Act: 2.6624. Min Act: -0.0000

Data Index: 1129706 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 3.5979. Min Range: -3.5979

Max Act: 2.4196. Min Act: -0.0000

Data Index: 517412 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 3.5979. Min Range: -3.5979

Max Act: 2.6211. Min Act: -0.0000

Data Index: 795199 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 3.5979. Min Range: -3.5979

Max Act: 2.2599. Min Act: -0.0000

Data Index: 523538 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 3.5979. Min Range: -3.5979

Max Act: 2.5652. Min Act: -0.0000

Data Index: 1308143 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 3.5979. Min Range: -3.5979

Max Act: 2.5848. Min Act: -0.0000

Data Index: 820757 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 3.5979. Min Range: -3.5979

Max Act: 2.6728. Min Act: -0.0000

Data Index: 1237020 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 3.5979. Min Range: -3.5979

Max Act: 2.5260. Min Act: -0.0000

Data Index: 1087078 (C4 (Web Text))

Max Activating Token Index: 445