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

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

Neuron 4465 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6645. Min Act: -0.0000

Data Index: 632123 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6615. Min Act: -0.0000

Data Index: 125740 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6276. Min Act: -0.0000

Data Index: 629812 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6326. Min Act: -0.0000

Data Index: 747890 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6467. Min Act: -0.0000

Data Index: 856845 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6386. Min Act: -0.0000

Data Index: 1216574 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5462. Min Act: -0.0000

Data Index: 173621 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5421. Min Act: -0.0000

Data Index: 651997 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5172. Min Act: -0.0000

Data Index: 624689 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5470. Min Act: -0.0000

Data Index: 243860 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5742. Min Act: -0.0000

Data Index: 594372 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4607. Min Act: -0.0000

Data Index: 335325 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5197. Min Act: -0.0000

Data Index: 410190 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4590. Min Act: -0.0000

Data Index: 823240 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5032. Min Act: -0.0000

Data Index: 164510 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4836. Min Act: -0.0000

Data Index: 221225 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5153. Min Act: -0.0000

Data Index: 452903 (C4 (Web Text))

Max Activating Token Index: 398

Text #17

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4951. Min Act: -0.0000

Data Index: 785977 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4644. Min Act: -0.0000

Data Index: 419415 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4711. Min Act: -0.0000

Data Index: 564961 (C4 (Web Text))

Max Activating Token Index: 360