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

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

Neuron 870 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: 0.0368. Min Range: -0.0368

Max Act: 0.0352. Min Act: -0.0006

Data Index: 1191669 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0368. Min Act: -0.0006

Data Index: 48860 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0359. Min Act: -0.0006

Data Index: 641864 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0356. Min Act: -0.0006

Data Index: 587515 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0349. Min Act: -0.0006

Data Index: 173474 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0341. Min Act: -0.0006

Data Index: 38675 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0345. Min Act: -0.0006

Data Index: 253485 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0352. Min Act: -0.0006

Data Index: 404648 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0332. Min Act: -0.0006

Data Index: 905424 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0336. Min Act: -0.0005

Data Index: 1137406 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0331. Min Act: -0.0006

Data Index: 508682 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0330. Min Act: -0.0006

Data Index: 330465 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0323. Min Act: -0.0006

Data Index: 257401 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0335. Min Act: -0.0006

Data Index: 635823 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0326. Min Act: -0.0006

Data Index: 955839 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0312. Min Act: -0.0006

Data Index: 165616 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0294. Min Act: -0.0006

Data Index: 973283 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0298. Min Act: -0.0006

Data Index: 1210712 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0309. Min Act: -0.0006

Data Index: 989723 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0303. Min Act: -0.0006

Data Index: 179573 (C4 (Web Text))

Max Activating Token Index: 190