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

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

Neuron 808 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4084. Min Range: -1.4084

Max Act: 1.4084. Min Act: -0.0001

Data Index: 4397 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 1.4084. Min Range: -1.4084

Max Act: 1.1187. Min Act: -0.0001

Data Index: 1271519 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 1.4084. Min Range: -1.4084

Max Act: 1.1500. Min Act: -0.0001

Data Index: 1250155 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 1.4084. Min Range: -1.4084

Max Act: 1.0544. Min Act: -0.0001

Data Index: 953804 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 1.4084. Min Range: -1.4084

Max Act: 0.8968. Min Act: -0.0001

Data Index: 868273 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 1.4084. Min Range: -1.4084

Max Act: 1.0881. Min Act: -0.0001

Data Index: 1073686 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 1.4084. Min Range: -1.4084

Max Act: 1.0484. Min Act: -0.0001

Data Index: 390557 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 1.4084. Min Range: -1.4084

Max Act: 1.0719. Min Act: -0.0001

Data Index: 856455 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 1.4084. Min Range: -1.4084

Max Act: 0.9318. Min Act: -0.0001

Data Index: 789607 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 1.4084. Min Range: -1.4084

Max Act: 1.0512. Min Act: -0.0001

Data Index: 760012 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 1.4084. Min Range: -1.4084

Max Act: 0.8308. Min Act: -0.0001

Data Index: 685916 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 1.4084. Min Range: -1.4084

Max Act: 0.9825. Min Act: -0.0001

Data Index: 293941 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 1.4084. Min Range: -1.4084

Max Act: 0.9452. Min Act: -0.0001

Data Index: 535923 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 1.4084. Min Range: -1.4084

Max Act: 0.9361. Min Act: -0.0001

Data Index: 1081517 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 1.4084. Min Range: -1.4084

Max Act: 0.9061. Min Act: -0.0001

Data Index: 697800 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 1.4084. Min Range: -1.4084

Max Act: 0.9481. Min Act: -0.0001

Data Index: 741455 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 1.4084. Min Range: -1.4084

Max Act: 0.8217. Min Act: -0.0001

Data Index: 744371 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 1.4084. Min Range: -1.4084

Max Act: 0.6052. Min Act: -0.0001

Data Index: 960281 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 1.4084. Min Range: -1.4084

Max Act: 0.8864. Min Act: -0.0001

Data Index: 128803 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 1.4084. Min Range: -1.4084

Max Act: 0.8718. Min Act: -0.0001

Data Index: 254379 (C4 (Web Text))

Max Activating Token Index: 394