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

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

Neuron 663 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4797. Min Range: -2.4797

Max Act: 2.4737. Min Act: -0.0000

Data Index: 160553 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 2.4797. Min Range: -2.4797

Max Act: 2.3056. Min Act: -0.0000

Data Index: 93598 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 2.4797. Min Range: -2.4797

Max Act: 2.4797. Min Act: -0.0000

Data Index: 349266 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 2.4797. Min Range: -2.4797

Max Act: 2.3002. Min Act: -0.0000

Data Index: 592415 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 2.4797. Min Range: -2.4797

Max Act: 2.1461. Min Act: -0.0000

Data Index: 1061089 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 2.4797. Min Range: -2.4797

Max Act: 2.0991. Min Act: -0.0000

Data Index: 309605 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 2.4797. Min Range: -2.4797

Max Act: 2.1001. Min Act: -0.0000

Data Index: 104534 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 2.4797. Min Range: -2.4797

Max Act: 2.1009. Min Act: -0.0001

Data Index: 1130248 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 2.4797. Min Range: -2.4797

Max Act: 2.0682. Min Act: -0.0000

Data Index: 1577489 (Python Code)

Max Activating Token Index: 384

Text #9

Max Range: 2.4797. Min Range: -2.4797

Max Act: 2.0210. Min Act: -0.0000

Data Index: 1204881 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 2.4797. Min Range: -2.4797

Max Act: 2.1186. Min Act: -0.0000

Data Index: 599368 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 2.4797. Min Range: -2.4797

Max Act: 1.8933. Min Act: -0.0000

Data Index: 158576 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 2.4797. Min Range: -2.4797

Max Act: 2.0862. Min Act: -0.0000

Data Index: 581410 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 2.4797. Min Range: -2.4797

Max Act: 1.8869. Min Act: -0.0000

Data Index: 900809 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 2.4797. Min Range: -2.4797

Max Act: 1.8602. Min Act: -0.0001

Data Index: 18933 (C4 (Web Text))

Max Activating Token Index: 237

Text #15

Max Range: 2.4797. Min Range: -2.4797

Max Act: 1.9276. Min Act: -0.0000

Data Index: 233302 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 2.4797. Min Range: -2.4797

Max Act: 1.8346. Min Act: -0.0000

Data Index: 682471 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 2.4797. Min Range: -2.4797

Max Act: 1.8295. Min Act: -0.0000

Data Index: 352458 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 2.4797. Min Range: -2.4797

Max Act: 1.7232. Min Act: -0.0000

Data Index: 750945 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 2.4797. Min Range: -2.4797

Max Act: 1.8741. Min Act: -0.0000

Data Index: 427983 (C4 (Web Text))

Max Activating Token Index: 530