Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4462 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0247. Min Range: -3.0247

Max Act: 2.8800. Min Act: -0.0000

Data Index: 202202 (C4 (Web Text))

Max Activating Token Index: 685

Text #1

Max Range: 3.0247. Min Range: -3.0247

Max Act: 3.0072. Min Act: -0.0000

Data Index: 297627 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 3.0247. Min Range: -3.0247

Max Act: 2.7489. Min Act: -0.0000

Data Index: 112254 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 3.0247. Min Range: -3.0247

Max Act: 2.8757. Min Act: -0.0000

Data Index: 1272519 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 3.0247. Min Range: -3.0247

Max Act: 3.0247. Min Act: -0.0000

Data Index: 534582 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 3.0247. Min Range: -3.0247

Max Act: 2.8430. Min Act: -0.0000

Data Index: 700112 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 3.0247. Min Range: -3.0247

Max Act: 2.6136. Min Act: -0.0000

Data Index: 567907 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 3.0247. Min Range: -3.0247

Max Act: 2.7032. Min Act: -0.0000

Data Index: 779311 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 3.0247. Min Range: -3.0247

Max Act: 2.6947. Min Act: -0.0000

Data Index: 1217094 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 3.0247. Min Range: -3.0247

Max Act: 2.5652. Min Act: -0.0000

Data Index: 1109632 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 3.0247. Min Range: -3.0247

Max Act: 2.5467. Min Act: -0.0000

Data Index: 641482 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 3.0247. Min Range: -3.0247

Max Act: 2.5225. Min Act: -0.0000

Data Index: 222096 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 3.0247. Min Range: -3.0247

Max Act: 2.4696. Min Act: -0.0000

Data Index: 211108 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 3.0247. Min Range: -3.0247

Max Act: 2.5996. Min Act: -0.0000

Data Index: 916712 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 3.0247. Min Range: -3.0247

Max Act: 2.3271. Min Act: -0.0000

Data Index: 1032497 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 3.0247. Min Range: -3.0247

Max Act: 2.4479. Min Act: -0.0000

Data Index: 1222358 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 3.0247. Min Range: -3.0247

Max Act: 2.1728. Min Act: -0.0000

Data Index: 538118 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 3.0247. Min Range: -3.0247

Max Act: 2.4258. Min Act: -0.0000

Data Index: 821846 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 3.0247. Min Range: -3.0247

Max Act: 2.5237. Min Act: -0.0000

Data Index: 727832 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 3.0247. Min Range: -3.0247

Max Act: 2.5207. Min Act: -0.0000

Data Index: 582321 (C4 (Web Text))

Max Activating Token Index: 378