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

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

Neuron 2975 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: 0.6470. Min Range: -0.6470

Max Act: 0.6244. Min Act: -0.0000

Data Index: 178559 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.6470. Min Act: -0.0000

Data Index: 786090 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.5514. Min Act: -0.0000

Data Index: 709079 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.5249. Min Act: -0.0000

Data Index: 802540 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.4923. Min Act: -0.0000

Data Index: 215307 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.4670. Min Act: -0.0000

Data Index: 76095 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.4331. Min Act: -0.0000

Data Index: 359211 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.4684. Min Act: -0.0000

Data Index: 958463 (C4 (Web Text))

Max Activating Token Index: 448

Text #8

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.4258. Min Act: -0.0000

Data Index: 32850 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.4118. Min Act: -0.0000

Data Index: 752229 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.3409. Min Act: -0.0000

Data Index: 492090 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.3965. Min Act: -0.0000

Data Index: 990394 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.3812. Min Act: -0.0000

Data Index: 855787 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.3929. Min Act: -0.0000

Data Index: 777033 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.3440. Min Act: -0.0000

Data Index: 337160 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.3569. Min Act: -0.0000

Data Index: 937494 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.3696. Min Act: -0.0000

Data Index: 484713 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.3500. Min Act: -0.0000

Data Index: 1120343 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.3373. Min Act: -0.0000

Data Index: 354195 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.3720. Min Act: -0.0000

Data Index: 241914 (C4 (Web Text))

Max Activating Token Index: 200