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

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

Neuron 3915 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0161. Min Range: -4.0161

Max Act: 4.0161. Min Act: -0.0000

Data Index: 1212920 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 4.0161. Min Range: -4.0161

Max Act: 3.7326. Min Act: -0.0000

Data Index: 8152 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 4.0161. Min Range: -4.0161

Max Act: 3.9350. Min Act: -0.0000

Data Index: 921118 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 4.0161. Min Range: -4.0161

Max Act: 3.9145. Min Act: -0.0000

Data Index: 561279 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 4.0161. Min Range: -4.0161

Max Act: 3.7233. Min Act: -0.0000

Data Index: 936497 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 4.0161. Min Range: -4.0161

Max Act: 3.7106. Min Act: -0.0000

Data Index: 1174676 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 4.0161. Min Range: -4.0161

Max Act: 3.7062. Min Act: -0.0000

Data Index: 194149 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 4.0161. Min Range: -4.0161

Max Act: 3.8713. Min Act: -0.0000

Data Index: 887034 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 4.0161. Min Range: -4.0161

Max Act: 3.5258. Min Act: -0.0000

Data Index: 1230190 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 4.0161. Min Range: -4.0161

Max Act: 3.5860. Min Act: -0.0000

Data Index: 991472 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 4.0161. Min Range: -4.0161

Max Act: 3.6214. Min Act: -0.0000

Data Index: 700242 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 4.0161. Min Range: -4.0161

Max Act: 3.3727. Min Act: -0.0000

Data Index: 822149 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 4.0161. Min Range: -4.0161

Max Act: 3.4956. Min Act: -0.0000

Data Index: 822175 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 4.0161. Min Range: -4.0161

Max Act: 3.5010. Min Act: -0.0000

Data Index: 1294082 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 4.0161. Min Range: -4.0161

Max Act: 3.4720. Min Act: -0.0000

Data Index: 155798 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 4.0161. Min Range: -4.0161

Max Act: 3.4829. Min Act: -0.0000

Data Index: 216074 (C4 (Web Text))

Max Activating Token Index: 821

Text #16

Max Range: 4.0161. Min Range: -4.0161

Max Act: 3.4639. Min Act: -0.0000

Data Index: 598116 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 4.0161. Min Range: -4.0161

Max Act: 3.6095. Min Act: -0.0000

Data Index: 824671 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 4.0161. Min Range: -4.0161

Max Act: 3.4045. Min Act: -0.0000

Data Index: 720721 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 4.0161. Min Range: -4.0161

Max Act: 3.2536. Min Act: -0.0000

Data Index: 1243202 (C4 (Web Text))

Max Activating Token Index: 731