Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 296 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0545. Min Act: -0.0005

Data Index: 299799 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0501. Min Act: -0.0005

Data Index: 846706 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0493. Min Act: -0.0005

Data Index: 451207 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0508. Min Act: -0.0005

Data Index: 1323051 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0476. Min Act: -0.0005

Data Index: 1047315 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0456. Min Act: -0.0005

Data Index: 364634 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0469. Min Act: -0.0005

Data Index: 282808 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0465. Min Act: -0.0005

Data Index: 194967 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0452. Min Act: -0.0005

Data Index: 1342813 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0461. Min Act: -0.0005

Data Index: 1041833 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0422. Min Act: -0.0005

Data Index: 954528 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0443. Min Act: -0.0005

Data Index: 518273 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0433. Min Act: -0.0005

Data Index: 1331417 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0436. Min Act: -0.0005

Data Index: 535702 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0426. Min Act: -0.0005

Data Index: 396695 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0442. Min Act: -0.0005

Data Index: 1035357 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0440. Min Act: -0.0005

Data Index: 281607 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0430. Min Act: -0.0005

Data Index: 954388 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0419. Min Act: -0.0005

Data Index: 104507 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0411. Min Act: -0.0005

Data Index: 420630 (C4 (Web Text))

Max Activating Token Index: 349