Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2488 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.5367. Min Act: -0.0001

Data Index: 1172384 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.5038. Min Act: -0.0001

Data Index: 1039617 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.4114. Min Act: -0.0001

Data Index: 1191809 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.4107. Min Act: -0.0001

Data Index: 1095120 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.3840. Min Act: -0.0001

Data Index: 332531 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.4083. Min Act: -0.0002

Data Index: 576330 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.3293. Min Act: -0.0001

Data Index: 978415 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.3797. Min Act: -0.0001

Data Index: 97997 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.3630. Min Act: -0.0001

Data Index: 545510 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.3693. Min Act: -0.0001

Data Index: 403945 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.3060. Min Act: -0.0001

Data Index: 965334 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.3318. Min Act: -0.0001

Data Index: 1035405 (C4 (Web Text))

Max Activating Token Index: 960

Text #12

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.3509. Min Act: -0.0001

Data Index: 1355703 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.3369. Min Act: -0.0001

Data Index: 351460 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.3756. Min Act: -0.0001

Data Index: 1335079 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.3563. Min Act: -0.0001

Data Index: 466247 (C4 (Web Text))

Max Activating Token Index: 479

Text #16

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.3446. Min Act: -0.0001

Data Index: 268299 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.3489. Min Act: -0.0001

Data Index: 1030186 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.3115. Min Act: -0.0001

Data Index: 547266 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.3417. Min Act: -0.0001

Data Index: 90670 (C4 (Web Text))

Max Activating Token Index: 875