Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 856 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1271. Min Range: -1.1271

Max Act: 1.1271. Min Act: -0.0001

Data Index: 1315601 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 1.1271. Min Range: -1.1271

Max Act: 1.0470. Min Act: -0.0001

Data Index: 805103 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.9669. Min Act: -0.0001

Data Index: 1336361 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.9676. Min Act: -0.0001

Data Index: 1200757 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.9048. Min Act: -0.0001

Data Index: 620759 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.8387. Min Act: -0.0001

Data Index: 1025398 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.8623. Min Act: -0.0001

Data Index: 315476 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.8552. Min Act: -0.0001

Data Index: 1096551 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.8350. Min Act: -0.0001

Data Index: 782679 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.9028. Min Act: -0.0001

Data Index: 105168 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.8223. Min Act: -0.0001

Data Index: 1158188 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.7985. Min Act: -0.0001

Data Index: 1097466 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.7631. Min Act: -0.0001

Data Index: 885354 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.7702. Min Act: -0.0001

Data Index: 693026 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.8340. Min Act: -0.0001

Data Index: 836880 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.8026. Min Act: -0.0001

Data Index: 439649 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.8023. Min Act: -0.0001

Data Index: 80626 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.8050. Min Act: -0.0001

Data Index: 1159865 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.7637. Min Act: -0.0001

Data Index: 719017 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.7633. Min Act: -0.0001

Data Index: 1232705 (C4 (Web Text))

Max Activating Token Index: 218