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

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

Neuron 2550 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: 0.5815. Min Range: -0.5815

Max Act: 0.5815. Min Act: -0.0001

Data Index: 1046718 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 0.5815. Min Range: -0.5815

Max Act: 0.5808. Min Act: -0.0000

Data Index: 626186 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.5815. Min Range: -0.5815

Max Act: 0.5164. Min Act: -0.0000

Data Index: 753870 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 0.5815. Min Range: -0.5815

Max Act: 0.4891. Min Act: -0.0001

Data Index: 915423 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 0.5815. Min Range: -0.5815

Max Act: 0.5197. Min Act: -0.0001

Data Index: 332823 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 0.5815. Min Range: -0.5815

Max Act: 0.4818. Min Act: -0.0001

Data Index: 575224 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 0.5815. Min Range: -0.5815

Max Act: 0.4593. Min Act: -0.0001

Data Index: 1200422 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 0.5815. Min Range: -0.5815

Max Act: 0.4590. Min Act: -0.0001

Data Index: 1106765 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.5815. Min Range: -0.5815

Max Act: 0.4573. Min Act: -0.0001

Data Index: 508769 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 0.5815. Min Range: -0.5815

Max Act: 0.4760. Min Act: -0.0001

Data Index: 1310863 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 0.5815. Min Range: -0.5815

Max Act: 0.4471. Min Act: -0.0001

Data Index: 1262335 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 0.5815. Min Range: -0.5815

Max Act: 0.4492. Min Act: -0.0001

Data Index: 452155 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 0.5815. Min Range: -0.5815

Max Act: 0.4607. Min Act: -0.0001

Data Index: 889186 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 0.5815. Min Range: -0.5815

Max Act: 0.4513. Min Act: -0.0000

Data Index: 812755 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 0.5815. Min Range: -0.5815

Max Act: 0.4440. Min Act: -0.0001

Data Index: 1141422 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 0.5815. Min Range: -0.5815

Max Act: 0.4361. Min Act: -0.0000

Data Index: 234018 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 0.5815. Min Range: -0.5815

Max Act: 0.4340. Min Act: -0.0001

Data Index: 452714 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 0.5815. Min Range: -0.5815

Max Act: 0.4417. Min Act: -0.0001

Data Index: 534998 (C4 (Web Text))

Max Activating Token Index: 856

Text #18

Max Range: 0.5815. Min Range: -0.5815

Max Act: 0.4187. Min Act: -0.0001

Data Index: 1193264 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 0.5815. Min Range: -0.5815

Max Act: 0.4197. Min Act: -0.0000

Data Index: 1027944 (C4 (Web Text))

Max Activating Token Index: 442