Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1304 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1756. Min Act: -0.0006

Data Index: 498166 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1735. Min Act: -0.0006

Data Index: 1052137 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1540. Min Act: -0.0006

Data Index: 964834 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1418. Min Act: -0.0006

Data Index: 214256 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1416. Min Act: -0.0006

Data Index: 1353348 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1410. Min Act: -0.0006

Data Index: 874877 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1495. Min Act: -0.0006

Data Index: 835472 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1449. Min Act: -0.0006

Data Index: 1125880 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1422. Min Act: -0.0005

Data Index: 41997 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1458. Min Act: -0.0006

Data Index: 831385 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1359. Min Act: -0.0006

Data Index: 1163278 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1406. Min Act: -0.0005

Data Index: 78557 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1344. Min Act: -0.0006

Data Index: 1186103 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1388. Min Act: -0.0006

Data Index: 402407 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1415. Min Act: -0.0006

Data Index: 622336 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1407. Min Act: -0.0005

Data Index: 351367 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1348. Min Act: -0.0006

Data Index: 475441 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1340. Min Act: -0.0006

Data Index: 492665 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1312. Min Act: -0.0006

Data Index: 915960 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1254. Min Act: -0.0005

Data Index: 210506 (C4 (Web Text))

Max Activating Token Index: 291