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

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

Neuron 2709 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4702. Min Range: -1.4702

Max Act: 1.3900. Min Act: -0.0001

Data Index: 1289290 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 1.4702. Min Range: -1.4702

Max Act: 1.4613. Min Act: -0.0001

Data Index: 830389 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 1.4702. Min Range: -1.4702

Max Act: 1.4702. Min Act: -0.0001

Data Index: 23724 (C4 (Web Text))

Max Activating Token Index: 611

Text #3

Max Range: 1.4702. Min Range: -1.4702

Max Act: 1.3894. Min Act: -0.0001

Data Index: 147211 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 1.4702. Min Range: -1.4702

Max Act: 1.3784. Min Act: -0.0001

Data Index: 1258335 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 1.4702. Min Range: -1.4702

Max Act: 1.2427. Min Act: -0.0001

Data Index: 98473 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 1.4702. Min Range: -1.4702

Max Act: 1.3095. Min Act: -0.0001

Data Index: 594642 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 1.4702. Min Range: -1.4702

Max Act: 1.2618. Min Act: -0.0001

Data Index: 548902 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 1.4702. Min Range: -1.4702

Max Act: 1.2671. Min Act: -0.0001

Data Index: 817915 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 1.4702. Min Range: -1.4702

Max Act: 1.2029. Min Act: -0.0001

Data Index: 63391 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 1.4702. Min Range: -1.4702

Max Act: 1.2394. Min Act: -0.0001

Data Index: 969286 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 1.4702. Min Range: -1.4702

Max Act: 1.2316. Min Act: -0.0001

Data Index: 1038141 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 1.4702. Min Range: -1.4702

Max Act: 1.2962. Min Act: -0.0001

Data Index: 209274 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 1.4702. Min Range: -1.4702

Max Act: 1.2335. Min Act: -0.0001

Data Index: 277188 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 1.4702. Min Range: -1.4702

Max Act: 1.2520. Min Act: -0.0001

Data Index: 538296 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 1.4702. Min Range: -1.4702

Max Act: 1.2703. Min Act: -0.0001

Data Index: 1714 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 1.4702. Min Range: -1.4702

Max Act: 1.2455. Min Act: -0.0001

Data Index: 358556 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 1.4702. Min Range: -1.4702

Max Act: 1.2482. Min Act: -0.0001

Data Index: 1270392 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 1.4702. Min Range: -1.4702

Max Act: 1.2071. Min Act: -0.0001

Data Index: 61533 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 1.4702. Min Range: -1.4702

Max Act: 1.2529. Min Act: -0.0001

Data Index: 419207 (C4 (Web Text))

Max Activating Token Index: 364