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

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

Neuron 1614 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0476. Min Act: -0.0004

Data Index: 606247 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0437. Min Act: -0.0004

Data Index: 699617 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0405. Min Act: -0.0004

Data Index: 1010433 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0474. Min Act: -0.0004

Data Index: 244385 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0364. Min Act: -0.0004

Data Index: 938531 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0419. Min Act: -0.0004

Data Index: 1311619 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0373. Min Act: -0.0004

Data Index: 1270580 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0385. Min Act: -0.0004

Data Index: 1040210 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0375. Min Act: -0.0004

Data Index: 337571 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0366. Min Act: -0.0004

Data Index: 1275955 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0326. Min Act: -0.0004

Data Index: 15288 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0331. Min Act: -0.0004

Data Index: 475831 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0329. Min Act: -0.0004

Data Index: 1049944 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0339. Min Act: -0.0004

Data Index: 737029 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0313. Min Act: -0.0004

Data Index: 347132 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0345. Min Act: -0.0004

Data Index: 266209 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0365. Min Act: -0.0004

Data Index: 283583 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0351. Min Act: -0.0004

Data Index: 1012702 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0335. Min Act: -0.0004

Data Index: 455372 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0323. Min Act: -0.0004

Data Index: 781439 (C4 (Web Text))

Max Activating Token Index: 412