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

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

Neuron 300 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.5412. Min Act: -0.0003

Data Index: 91820 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.5088. Min Act: -0.0003

Data Index: 357396 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4584. Min Act: -0.0003

Data Index: 652641 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4872. Min Act: -0.0003

Data Index: 152689 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4877. Min Act: -0.0003

Data Index: 429408 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4628. Min Act: -0.0003

Data Index: 369388 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4309. Min Act: -0.0003

Data Index: 980075 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4644. Min Act: -0.0003

Data Index: 561785 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.5011. Min Act: -0.0003

Data Index: 665526 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4686. Min Act: -0.0003

Data Index: 37693 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4486. Min Act: -0.0003

Data Index: 1184050 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4390. Min Act: -0.0003

Data Index: 1060131 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4134. Min Act: -0.0003

Data Index: 975919 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4514. Min Act: -0.0003

Data Index: 208933 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4509. Min Act: -0.0003

Data Index: 338119 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4240. Min Act: -0.0003

Data Index: 372239 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4104. Min Act: -0.0003

Data Index: 1220602 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4346. Min Act: -0.0003

Data Index: 554208 (C4 (Web Text))

Max Activating Token Index: 446

Text #18

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4321. Min Act: -0.0003

Data Index: 903024 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4178. Min Act: -0.0003

Data Index: 276620 (C4 (Web Text))

Max Activating Token Index: 604