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

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

Neuron 3055 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9260. Min Range: -2.9260

Max Act: 2.9260. Min Act: -0.0000

Data Index: 1202508 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 2.9260. Min Range: -2.9260

Max Act: 2.5985. Min Act: -0.0000

Data Index: 481030 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 2.9260. Min Range: -2.9260

Max Act: 2.4686. Min Act: -0.0000

Data Index: 816969 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 2.9260. Min Range: -2.9260

Max Act: 2.2840. Min Act: -0.0000

Data Index: 1238489 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 2.9260. Min Range: -2.9260

Max Act: 2.2983. Min Act: -0.0000

Data Index: 904598 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 2.9260. Min Range: -2.9260

Max Act: 2.3170. Min Act: -0.0000

Data Index: 138569 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 2.9260. Min Range: -2.9260

Max Act: 2.2032. Min Act: -0.0000

Data Index: 790562 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 2.9260. Min Range: -2.9260

Max Act: 2.1937. Min Act: -0.0000

Data Index: 321922 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 2.9260. Min Range: -2.9260

Max Act: 2.1790. Min Act: -0.0000

Data Index: 860791 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 2.9260. Min Range: -2.9260

Max Act: 2.0632. Min Act: -0.0000

Data Index: 465326 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 2.9260. Min Range: -2.9260

Max Act: 1.8947. Min Act: -0.0000

Data Index: 455674 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 2.9260. Min Range: -2.9260

Max Act: 2.0885. Min Act: -0.0000

Data Index: 1336837 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 2.9260. Min Range: -2.9260

Max Act: 1.9705. Min Act: -0.0000

Data Index: 1332286 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 2.9260. Min Range: -2.9260

Max Act: 1.9037. Min Act: -0.0000

Data Index: 804848 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 2.9260. Min Range: -2.9260

Max Act: 1.9037. Min Act: -0.0000

Data Index: 739453 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 2.9260. Min Range: -2.9260

Max Act: 1.7854. Min Act: -0.0000

Data Index: 667854 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 2.9260. Min Range: -2.9260

Max Act: 1.7640. Min Act: -0.0000

Data Index: 495416 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 2.9260. Min Range: -2.9260

Max Act: 2.0990. Min Act: -0.0000

Data Index: 1247983 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 2.9260. Min Range: -2.9260

Max Act: 1.8421. Min Act: -0.0000

Data Index: 681006 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 2.9260. Min Range: -2.9260

Max Act: 1.8537. Min Act: -0.0000

Data Index: 224043 (C4 (Web Text))

Max Activating Token Index: 821