Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 312 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.4876. Min Act: -0.0001

Data Index: 549957 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.4638. Min Act: -0.0001

Data Index: 106067 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3554. Min Act: -0.0001

Data Index: 1326717 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3909. Min Act: -0.0001

Data Index: 1014403 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.4280. Min Act: -0.0001

Data Index: 896715 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3847. Min Act: -0.0001

Data Index: 692128 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3840. Min Act: -0.0001

Data Index: 1194739 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3855. Min Act: -0.0001

Data Index: 502380 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3897. Min Act: -0.0001

Data Index: 1067811 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3668. Min Act: -0.0001

Data Index: 28882 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3543. Min Act: -0.0001

Data Index: 1332614 (C4 (Web Text))

Max Activating Token Index: 323

Text #11

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3642. Min Act: -0.0001

Data Index: 877468 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3660. Min Act: -0.0001

Data Index: 904501 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3913. Min Act: -0.0001

Data Index: 1304489 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3728. Min Act: -0.0001

Data Index: 1014353 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3369. Min Act: -0.0001

Data Index: 1064479 (C4 (Web Text))

Max Activating Token Index: 975

Text #16

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3537. Min Act: -0.0001

Data Index: 1335973 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3056. Min Act: -0.0001

Data Index: 680226 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3391. Min Act: -0.0001

Data Index: 255885 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3441. Min Act: -0.0001

Data Index: 809161 (C4 (Web Text))

Max Activating Token Index: 921