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

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

Neuron 25 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: 0.5229. Min Range: -0.5229

Max Act: 0.5229. Min Act: -0.0000

Data Index: 1551002 (Python Code)

Max Activating Token Index: 322

Text #1

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.4800. Min Act: -0.0000

Data Index: 440637 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.3889. Min Act: -0.0000

Data Index: 1650034 (Python Code)

Max Activating Token Index: 568

Text #3

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.4161. Min Act: -0.0000

Data Index: 147797 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.4011. Min Act: -0.0000

Data Index: 311252 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.4114. Min Act: -0.0000

Data Index: 966611 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.4083. Min Act: -0.0000

Data Index: 1534113 (Python Code)

Max Activating Token Index: 498

Text #7

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.3979. Min Act: -0.0000

Data Index: 945817 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.3896. Min Act: -0.0000

Data Index: 6806 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.3439. Min Act: -0.0000

Data Index: 917463 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.3492. Min Act: -0.0000

Data Index: 718434 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.3396. Min Act: -0.0000

Data Index: 1000055 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.3527. Min Act: -0.0000

Data Index: 880775 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.3256. Min Act: -0.0000

Data Index: 663066 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.3015. Min Act: -0.0000

Data Index: 1128469 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.3089. Min Act: -0.0000

Data Index: 1017584 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.3355. Min Act: -0.0000

Data Index: 1294723 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.2906. Min Act: -0.0000

Data Index: 694145 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.3119. Min Act: -0.0000

Data Index: 424104 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.5229. Min Range: -0.5229

Max Act: 0.3106. Min Act: -0.0000

Data Index: 999094 (C4 (Web Text))

Max Activating Token Index: 29