Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2267 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.8119. Min Range: -3.8119

Max Act: 3.8119. Min Act: -0.0000

Data Index: 18234 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 3.8119. Min Range: -3.8119

Max Act: 3.6042. Min Act: -0.0000

Data Index: 1189854 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 3.8119. Min Range: -3.8119

Max Act: 3.5742. Min Act: -0.0000

Data Index: 413403 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 3.8119. Min Range: -3.8119

Max Act: 3.7579. Min Act: -0.0000

Data Index: 245449 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 3.8119. Min Range: -3.8119

Max Act: 3.3577. Min Act: -0.0000

Data Index: 645724 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 3.8119. Min Range: -3.8119

Max Act: 3.7142. Min Act: -0.0000

Data Index: 493963 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 3.8119. Min Range: -3.8119

Max Act: 3.5047. Min Act: -0.0000

Data Index: 1103238 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 3.8119. Min Range: -3.8119

Max Act: 3.2703. Min Act: -0.0001

Data Index: 308694 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 3.8119. Min Range: -3.8119

Max Act: 2.9781. Min Act: -0.0000

Data Index: 1242800 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 3.8119. Min Range: -3.8119

Max Act: 2.9595. Min Act: -0.0000

Data Index: 1206417 (C4 (Web Text))

Max Activating Token Index: 922

Text #10

Max Range: 3.8119. Min Range: -3.8119

Max Act: 2.9361. Min Act: -0.0001

Data Index: 749267 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 3.8119. Min Range: -3.8119

Max Act: 3.0723. Min Act: -0.0000

Data Index: 1343371 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 3.8119. Min Range: -3.8119

Max Act: 2.9223. Min Act: -0.0000

Data Index: 929015 (C4 (Web Text))

Max Activating Token Index: 551

Text #13

Max Range: 3.8119. Min Range: -3.8119

Max Act: 2.7414. Min Act: -0.0000

Data Index: 917761 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 3.8119. Min Range: -3.8119

Max Act: 2.7445. Min Act: -0.0000

Data Index: 202169 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 3.8119. Min Range: -3.8119

Max Act: 3.1090. Min Act: -0.0000

Data Index: 695070 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 3.8119. Min Range: -3.8119

Max Act: 2.6655. Min Act: -0.0000

Data Index: 1060858 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 3.8119. Min Range: -3.8119

Max Act: 2.9074. Min Act: -0.0000

Data Index: 896430 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 3.8119. Min Range: -3.8119

Max Act: 2.4079. Min Act: -0.0001

Data Index: 151491 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 3.8119. Min Range: -3.8119

Max Act: 2.7036. Min Act: -0.0000

Data Index: 730316 (C4 (Web Text))

Max Activating Token Index: 723