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

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

Neuron 4837 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.7400. Min Act: -0.0001

Data Index: 1028040 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.7302. Min Act: -0.0001

Data Index: 549197 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.7915. Min Act: -0.0001

Data Index: 370779 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.7358. Min Act: -0.0001

Data Index: 248554 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.7298. Min Act: -0.0001

Data Index: 384926 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.7261. Min Act: -0.0001

Data Index: 1146361 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.6620. Min Act: -0.0001

Data Index: 1233394 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.7571. Min Act: -0.0001

Data Index: 1302083 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.6412. Min Act: -0.0001

Data Index: 423730 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.7139. Min Act: -0.0001

Data Index: 283994 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.6573. Min Act: -0.0001

Data Index: 971042 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.6585. Min Act: -0.0001

Data Index: 882678 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.7149. Min Act: -0.0001

Data Index: 139299 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.6680. Min Act: -0.0001

Data Index: 849158 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.7307. Min Act: -0.0001

Data Index: 945160 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.6920. Min Act: -0.0001

Data Index: 1227844 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.6930. Min Act: -0.0001

Data Index: 854657 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.6697. Min Act: -0.0001

Data Index: 748323 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.6913. Min Act: -0.0001

Data Index: 984600 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.6641. Min Act: -0.0001

Data Index: 1157222 (C4 (Web Text))

Max Activating Token Index: 675