Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4136 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.7223. Min Act: -0.0000

Data Index: 910789 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.6403. Min Act: -0.0000

Data Index: 80095 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.5901. Min Act: -0.0000

Data Index: 892944 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.5502. Min Act: -0.0000

Data Index: 1102574 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.5948. Min Act: -0.0000

Data Index: 186276 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.5586. Min Act: -0.0000

Data Index: 344446 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.5811. Min Act: -0.0000

Data Index: 798466 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.5709. Min Act: -0.0000

Data Index: 56820 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.4442. Min Act: -0.0000

Data Index: 83466 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.6269. Min Act: -0.0000

Data Index: 1009324 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.5928. Min Act: -0.0000

Data Index: 751096 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.5545. Min Act: -0.0000

Data Index: 675286 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.5503. Min Act: -0.0000

Data Index: 1190708 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.5443. Min Act: -0.0000

Data Index: 55575 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.5641. Min Act: -0.0000

Data Index: 1334656 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.4991. Min Act: -0.0000

Data Index: 903725 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.5316. Min Act: -0.0000

Data Index: 369703 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.5294. Min Act: -0.0000

Data Index: 141767 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.5420. Min Act: -0.0000

Data Index: 46541 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.5289. Min Act: -0.0000

Data Index: 1066573 (C4 (Web Text))

Max Activating Token Index: 853