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

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

Neuron 4501 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4516. Min Range: -4.4516

Max Act: 4.4516. Min Act: -0.0000

Data Index: 36347 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 4.4516. Min Range: -4.4516

Max Act: 4.3460. Min Act: -0.0000

Data Index: 723180 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 4.4516. Min Range: -4.4516

Max Act: 4.1617. Min Act: -0.0000

Data Index: 305350 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 4.4516. Min Range: -4.4516

Max Act: 4.3352. Min Act: -0.0000

Data Index: 1115049 (C4 (Web Text))

Max Activating Token Index: 354

Text #4

Max Range: 4.4516. Min Range: -4.4516

Max Act: 4.1726. Min Act: -0.0000

Data Index: 742822 (C4 (Web Text))

Max Activating Token Index: 425

Text #5

Max Range: 4.4516. Min Range: -4.4516

Max Act: 4.0522. Min Act: -0.0000

Data Index: 380843 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 4.4516. Min Range: -4.4516

Max Act: 4.1371. Min Act: -0.0000

Data Index: 486804 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 4.4516. Min Range: -4.4516

Max Act: 3.9365. Min Act: -0.0000

Data Index: 634911 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 4.4516. Min Range: -4.4516

Max Act: 4.0488. Min Act: -0.0000

Data Index: 1096948 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 4.4516. Min Range: -4.4516

Max Act: 3.8787. Min Act: -0.0000

Data Index: 580111 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 4.4516. Min Range: -4.4516

Max Act: 3.8513. Min Act: -0.0000

Data Index: 99977 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 4.4516. Min Range: -4.4516

Max Act: 3.9673. Min Act: -0.0000

Data Index: 435949 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 4.4516. Min Range: -4.4516

Max Act: 3.8785. Min Act: -0.0000

Data Index: 701485 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 4.4516. Min Range: -4.4516

Max Act: 3.4277. Min Act: -0.0000

Data Index: 1192143 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 4.4516. Min Range: -4.4516

Max Act: 3.5138. Min Act: -0.0000

Data Index: 218463 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 4.4516. Min Range: -4.4516

Max Act: 3.6130. Min Act: -0.0000

Data Index: 962415 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 4.4516. Min Range: -4.4516

Max Act: 3.4383. Min Act: -0.0000

Data Index: 460830 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 4.4516. Min Range: -4.4516

Max Act: 3.2261. Min Act: -0.0000

Data Index: 957009 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 4.4516. Min Range: -4.4516

Max Act: 3.1888. Min Act: -0.0000

Data Index: 926736 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 4.4516. Min Range: -4.4516

Max Act: 3.1425. Min Act: -0.0000

Data Index: 1269493 (C4 (Web Text))

Max Activating Token Index: 860