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

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

Neuron 5610 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3226. Min Range: -2.3226

Max Act: 2.3226. Min Act: -0.0000

Data Index: 208402 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 2.3226. Min Range: -2.3226

Max Act: 2.1245. Min Act: -0.0000

Data Index: 1639036 (Python Code)

Max Activating Token Index: 150

Text #2

Max Range: 2.3226. Min Range: -2.3226

Max Act: 1.9921. Min Act: -0.0000

Data Index: 371672 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 2.3226. Min Range: -2.3226

Max Act: 1.8830. Min Act: -0.0000

Data Index: 904365 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 2.3226. Min Range: -2.3226

Max Act: 1.8179. Min Act: -0.0000

Data Index: 508216 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 2.3226. Min Range: -2.3226

Max Act: 1.8052. Min Act: -0.0000

Data Index: 447609 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 2.3226. Min Range: -2.3226

Max Act: 1.6866. Min Act: -0.0000

Data Index: 703110 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 2.3226. Min Range: -2.3226

Max Act: 1.5986. Min Act: -0.0000

Data Index: 1641388 (Python Code)

Max Activating Token Index: 210

Text #8

Max Range: 2.3226. Min Range: -2.3226

Max Act: 1.7192. Min Act: -0.0000

Data Index: 263240 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 2.3226. Min Range: -2.3226

Max Act: 1.6061. Min Act: -0.0000

Data Index: 1310310 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 2.3226. Min Range: -2.3226

Max Act: 2.0069. Min Act: -0.0000

Data Index: 1344871 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 2.3226. Min Range: -2.3226

Max Act: 1.6314. Min Act: -0.0000

Data Index: 1422737 (Python Code)

Max Activating Token Index: 961

Text #12

Max Range: 2.3226. Min Range: -2.3226

Max Act: 1.6239. Min Act: -0.0000

Data Index: 1034824 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 2.3226. Min Range: -2.3226

Max Act: 1.6002. Min Act: -0.0000

Data Index: 1505801 (Python Code)

Max Activating Token Index: 984

Text #14

Max Range: 2.3226. Min Range: -2.3226

Max Act: 1.6821. Min Act: -0.0000

Data Index: 818018 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 2.3226. Min Range: -2.3226

Max Act: 1.5570. Min Act: -0.0000

Data Index: 1175749 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 2.3226. Min Range: -2.3226

Max Act: 1.6733. Min Act: -0.0000

Data Index: 1523275 (Python Code)

Max Activating Token Index: 464

Text #17

Max Range: 2.3226. Min Range: -2.3226

Max Act: 1.5650. Min Act: -0.0000

Data Index: 871731 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 2.3226. Min Range: -2.3226

Max Act: 1.4686. Min Act: -0.0000

Data Index: 163793 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 2.3226. Min Range: -2.3226

Max Act: 1.5417. Min Act: -0.0000

Data Index: 1053544 (C4 (Web Text))

Max Activating Token Index: 589