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

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

Neuron 638 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3593. Min Range: -3.3593

Max Act: 3.3593. Min Act: -0.0000

Data Index: 209451 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 3.3593. Min Range: -3.3593

Max Act: 2.7510. Min Act: -0.0000

Data Index: 239114 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 3.3593. Min Range: -3.3593

Max Act: 3.0201. Min Act: -0.0000

Data Index: 201840 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 3.3593. Min Range: -3.3593

Max Act: 2.7220. Min Act: -0.0000

Data Index: 279316 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 3.3593. Min Range: -3.3593

Max Act: 2.7057. Min Act: -0.0000

Data Index: 447076 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 3.3593. Min Range: -3.3593

Max Act: 3.1282. Min Act: -0.0000

Data Index: 994825 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 3.3593. Min Range: -3.3593

Max Act: 2.5882. Min Act: -0.0000

Data Index: 1223884 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 3.3593. Min Range: -3.3593

Max Act: 2.7383. Min Act: -0.0000

Data Index: 838168 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 3.3593. Min Range: -3.3593

Max Act: 2.4367. Min Act: -0.0000

Data Index: 25029 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 3.3593. Min Range: -3.3593

Max Act: 2.4708. Min Act: -0.0000

Data Index: 564137 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 3.3593. Min Range: -3.3593

Max Act: 2.4437. Min Act: -0.0000

Data Index: 1131241 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 3.3593. Min Range: -3.3593

Max Act: 2.4339. Min Act: -0.0000

Data Index: 347001 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 3.3593. Min Range: -3.3593

Max Act: 2.3618. Min Act: -0.0000

Data Index: 584747 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 3.3593. Min Range: -3.3593

Max Act: 2.3560. Min Act: -0.0001

Data Index: 626598 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 3.3593. Min Range: -3.3593

Max Act: 2.2242. Min Act: -0.0000

Data Index: 476350 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 3.3593. Min Range: -3.3593

Max Act: 2.3418. Min Act: -0.0000

Data Index: 1181026 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 3.3593. Min Range: -3.3593

Max Act: 2.3696. Min Act: -0.0000

Data Index: 910360 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 3.3593. Min Range: -3.3593

Max Act: 2.2555. Min Act: -0.0000

Data Index: 933926 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 3.3593. Min Range: -3.3593

Max Act: 1.8234. Min Act: -0.0000

Data Index: 68246 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 3.3593. Min Range: -3.3593

Max Act: 2.2449. Min Act: -0.0000

Data Index: 118843 (C4 (Web Text))

Max Activating Token Index: 346