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

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

Neuron 3194 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: 2.1764. Min Range: -2.1764

Max Act: 2.1764. Min Act: 0.0000

Data Index: 614092 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.6792. Min Act: 0.0003

Data Index: 73163 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.5990. Min Act: -0.0000

Data Index: 1190660 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.4593. Min Act: -0.0000

Data Index: 286818 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.3562. Min Act: -0.0000

Data Index: 71477 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.3931. Min Act: 0.0002

Data Index: 363978 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.4172. Min Act: -0.0000

Data Index: 299205 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.3971. Min Act: 0.0000

Data Index: 663320 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.3568. Min Act: -0.0000

Data Index: 445631 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.3793. Min Act: -0.0000

Data Index: 1149465 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.3217. Min Act: 0.0001

Data Index: 864737 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.3223. Min Act: -0.0000

Data Index: 897164 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.2793. Min Act: -0.0000

Data Index: 1094954 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.2170. Min Act: -0.0000

Data Index: 153527 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.1360. Min Act: -0.0000

Data Index: 38597 (C4 (Web Text))

Max Activating Token Index: 597

Text #15

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.1404. Min Act: 0.0001

Data Index: 770126 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.1583. Min Act: -0.0000

Data Index: 141481 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.1440. Min Act: 0.0007

Data Index: 1267161 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.1243. Min Act: -0.0000

Data Index: 1175622 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.1768. Min Act: -0.0000

Data Index: 302205 (C4 (Web Text))

Max Activating Token Index: 57