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

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

Neuron 1123 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: 0.0403. Min Range: -0.0403

Max Act: 0.0403. Min Act: -0.0005

Data Index: 209987 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0398. Min Act: -0.0005

Data Index: 122955 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0381. Min Act: -0.0005

Data Index: 405289 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0380. Min Act: -0.0005

Data Index: 407497 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0358. Min Act: -0.0005

Data Index: 960124 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0354. Min Act: -0.0005

Data Index: 638426 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0361. Min Act: -0.0005

Data Index: 1328481 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0347. Min Act: -0.0005

Data Index: 235674 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0355. Min Act: -0.0005

Data Index: 1349456 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0360. Min Act: -0.0005

Data Index: 203608 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0354. Min Act: -0.0005

Data Index: 383037 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0340. Min Act: -0.0005

Data Index: 1078012 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0315. Min Act: -0.0005

Data Index: 596494 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0360. Min Act: -0.0005

Data Index: 1240145 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0338. Min Act: -0.0005

Data Index: 43553 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0333. Min Act: -0.0005

Data Index: 1145209 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0332. Min Act: -0.0005

Data Index: 1133275 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0344. Min Act: -0.0005

Data Index: 457096 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0344. Min Act: -0.0005

Data Index: 1341955 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0335. Min Act: -0.0005

Data Index: 437165 (C4 (Web Text))

Max Activating Token Index: 804