Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1256 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.6084. Min Act: -0.0000

Data Index: 589337 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.5956. Min Act: -0.0001

Data Index: 732546 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4893. Min Act: -0.0001

Data Index: 1043315 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.5208. Min Act: -0.0001

Data Index: 791834 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4700. Min Act: -0.0000

Data Index: 620820 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.5305. Min Act: -0.0000

Data Index: 180199 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4694. Min Act: -0.0000

Data Index: 1172729 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4493. Min Act: -0.0001

Data Index: 968698 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4350. Min Act: -0.0001

Data Index: 519237 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4440. Min Act: -0.0001

Data Index: 470101 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4308. Min Act: -0.0000

Data Index: 360230 (C4 (Web Text))

Max Activating Token Index: 1018

Text #11

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4379. Min Act: -0.0000

Data Index: 1232789 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4251. Min Act: -0.0000

Data Index: 523438 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4520. Min Act: -0.0001

Data Index: 1202952 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4389. Min Act: -0.0000

Data Index: 357724 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4469. Min Act: -0.0001

Data Index: 203649 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4026. Min Act: -0.0000

Data Index: 862981 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.3965. Min Act: -0.0001

Data Index: 681960 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4039. Min Act: -0.0001

Data Index: 1293011 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.3707. Min Act: -0.0000

Data Index: 1029854 (C4 (Web Text))

Max Activating Token Index: 101