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

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

Neuron 3459 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: 2.0669. Min Range: -2.0669

Max Act: 2.0669. Min Act: -0.0000

Data Index: 750318 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.8215. Min Act: -0.0000

Data Index: 1188875 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.8534. Min Act: -0.0000

Data Index: 1249769 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.7554. Min Act: -0.0000

Data Index: 1000459 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.8222. Min Act: -0.0000

Data Index: 1171009 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.6920. Min Act: -0.0000

Data Index: 87440 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.6960. Min Act: -0.0000

Data Index: 951398 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.6497. Min Act: -0.0000

Data Index: 161093 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.7433. Min Act: -0.0000

Data Index: 295491 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.7244. Min Act: -0.0000

Data Index: 1093996 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.7103. Min Act: -0.0000

Data Index: 741636 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.6915. Min Act: -0.0000

Data Index: 691354 (C4 (Web Text))

Max Activating Token Index: 695

Text #12

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.6111. Min Act: -0.0000

Data Index: 678369 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.4890. Min Act: -0.0000

Data Index: 1276946 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.5639. Min Act: -0.0000

Data Index: 399511 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.6639. Min Act: -0.0000

Data Index: 437137 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.5731. Min Act: -0.0000

Data Index: 1119307 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.4695. Min Act: -0.0000

Data Index: 1037089 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.4278. Min Act: -0.0000

Data Index: 715593 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 2.0669. Min Range: -2.0669

Max Act: 1.5499. Min Act: -0.0000

Data Index: 227798 (C4 (Web Text))

Max Activating Token Index: 30