Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3598 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.7423. Min Act: -0.0000

Data Index: 1282918 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.6219. Min Act: -0.0000

Data Index: 364615 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.5716. Min Act: -0.0000

Data Index: 1036082 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.5866. Min Act: -0.0000

Data Index: 977347 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.5332. Min Act: -0.0000

Data Index: 1288992 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.5300. Min Act: -0.0000

Data Index: 997400 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.5354. Min Act: -0.0000

Data Index: 926510 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.5674. Min Act: -0.0000

Data Index: 1143182 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.5185. Min Act: -0.0000

Data Index: 977196 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.5159. Min Act: -0.0000

Data Index: 482946 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.4850. Min Act: -0.0000

Data Index: 120714 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.4681. Min Act: -0.0000

Data Index: 164871 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.4931. Min Act: -0.0000

Data Index: 87205 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.4660. Min Act: -0.0000

Data Index: 649495 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.4225. Min Act: -0.0000

Data Index: 978357 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.4768. Min Act: -0.0000

Data Index: 523376 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.4560. Min Act: -0.0000

Data Index: 889260 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.4388. Min Act: -0.0000

Data Index: 401082 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.4218. Min Act: -0.0000

Data Index: 124595 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.4319. Min Act: -0.0000

Data Index: 178417 (C4 (Web Text))

Max Activating Token Index: 349