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

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

Neuron 796 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.6983. Min Act: -0.0000

Data Index: 247781 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.6399. Min Act: -0.0000

Data Index: 1109155 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.5752. Min Act: 0.0002

Data Index: 656980 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.5951. Min Act: -0.0000

Data Index: 1126544 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.5758. Min Act: 0.0001

Data Index: 1225133 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.5526. Min Act: 0.0002

Data Index: 480513 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.5470. Min Act: -0.0000

Data Index: 1130630 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.5371. Min Act: 0.0000

Data Index: 74433 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.5187. Min Act: -0.0000

Data Index: 445307 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.5026. Min Act: -0.0000

Data Index: 994554 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.4718. Min Act: -0.0000

Data Index: 599699 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.4735. Min Act: 0.0000

Data Index: 431823 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.4502. Min Act: -0.0000

Data Index: 396551 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.4797. Min Act: -0.0000

Data Index: 574848 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.4708. Min Act: -0.0000

Data Index: 996376 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.4885. Min Act: 0.0001

Data Index: 1033486 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.4370. Min Act: -0.0000

Data Index: 947658 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.4645. Min Act: -0.0000

Data Index: 538888 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.4479. Min Act: -0.0000

Data Index: 358837 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.4872. Min Act: -0.0000

Data Index: 1066784 (C4 (Web Text))

Max Activating Token Index: 169