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

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

Neuron 2227 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1668. Min Range: -2.1668

Max Act: 2.1668. Min Act: -0.0000

Data Index: 134359 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 2.1668. Min Range: -2.1668

Max Act: 1.8355. Min Act: -0.0000

Data Index: 132248 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 2.1668. Min Range: -2.1668

Max Act: 1.6082. Min Act: -0.0000

Data Index: 54752 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 2.1668. Min Range: -2.1668

Max Act: 1.5133. Min Act: -0.0000

Data Index: 727959 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 2.1668. Min Range: -2.1668

Max Act: 1.3266. Min Act: -0.0000

Data Index: 1543029 (Python Code)

Max Activating Token Index: 532

Text #5

Max Range: 2.1668. Min Range: -2.1668

Max Act: 1.2135. Min Act: -0.0000

Data Index: 181234 (C4 (Web Text))

Max Activating Token Index: 211

Text #6

Max Range: 2.1668. Min Range: -2.1668

Max Act: 1.3480. Min Act: -0.0000

Data Index: 116690 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 2.1668. Min Range: -2.1668

Max Act: 1.2669. Min Act: -0.0000

Data Index: 1013165 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 2.1668. Min Range: -2.1668

Max Act: 1.1761. Min Act: -0.0000

Data Index: 378735 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 2.1668. Min Range: -2.1668

Max Act: 1.2457. Min Act: -0.0000

Data Index: 495620 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 2.1668. Min Range: -2.1668

Max Act: 1.3137. Min Act: -0.0000

Data Index: 1342914 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 2.1668. Min Range: -2.1668

Max Act: 1.2456. Min Act: -0.0000

Data Index: 1439993 (Python Code)

Max Activating Token Index: 41

Text #12

Max Range: 2.1668. Min Range: -2.1668

Max Act: 1.2265. Min Act: -0.0000

Data Index: 476671 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 2.1668. Min Range: -2.1668

Max Act: 1.2029. Min Act: -0.0000

Data Index: 264398 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 2.1668. Min Range: -2.1668

Max Act: 1.1986. Min Act: -0.0000

Data Index: 1208682 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 2.1668. Min Range: -2.1668

Max Act: 1.1860. Min Act: -0.0000

Data Index: 1428339 (Python Code)

Max Activating Token Index: 138

Text #16

Max Range: 2.1668. Min Range: -2.1668

Max Act: 1.1734. Min Act: 0.0000

Data Index: 1295598 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 2.1668. Min Range: -2.1668

Max Act: 1.1584. Min Act: 0.0000

Data Index: 723055 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 2.1668. Min Range: -2.1668

Max Act: 1.1760. Min Act: -0.0000

Data Index: 493540 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 2.1668. Min Range: -2.1668

Max Act: 1.2278. Min Act: 0.0000

Data Index: 920731 (C4 (Web Text))

Max Activating Token Index: 1000