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

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

Neuron 1560 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3340. Min Range: -2.3340

Max Act: 2.2402. Min Act: -0.0000

Data Index: 1007719 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 2.3340. Min Range: -2.3340

Max Act: 2.2790. Min Act: -0.0000

Data Index: 700387 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 2.3340. Min Range: -2.3340

Max Act: 2.3340. Min Act: -0.0000

Data Index: 875617 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 2.3340. Min Range: -2.3340

Max Act: 2.3254. Min Act: -0.0000

Data Index: 927420 (C4 (Web Text))

Max Activating Token Index: 302

Text #4

Max Range: 2.3340. Min Range: -2.3340

Max Act: 2.2164. Min Act: -0.0000

Data Index: 1322947 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 2.3340. Min Range: -2.3340

Max Act: 2.1284. Min Act: -0.0000

Data Index: 1458418 (Python Code)

Max Activating Token Index: 155

Text #6

Max Range: 2.3340. Min Range: -2.3340

Max Act: 2.1275. Min Act: -0.0000

Data Index: 105550 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 2.3340. Min Range: -2.3340

Max Act: 2.1289. Min Act: -0.0000

Data Index: 1030023 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 2.3340. Min Range: -2.3340

Max Act: 2.0022. Min Act: -0.0000

Data Index: 1293781 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 2.3340. Min Range: -2.3340

Max Act: 2.1151. Min Act: -0.0000

Data Index: 1355317 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 2.3340. Min Range: -2.3340

Max Act: 2.0821. Min Act: -0.0000

Data Index: 562873 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 2.3340. Min Range: -2.3340

Max Act: 2.1595. Min Act: -0.0000

Data Index: 1007079 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 2.3340. Min Range: -2.3340

Max Act: 2.1466. Min Act: -0.0000

Data Index: 427605 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 2.3340. Min Range: -2.3340

Max Act: 1.9710. Min Act: -0.0000

Data Index: 1549983 (Python Code)

Max Activating Token Index: 120

Text #14

Max Range: 2.3340. Min Range: -2.3340

Max Act: 1.9052. Min Act: -0.0000

Data Index: 188963 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 2.3340. Min Range: -2.3340

Max Act: 2.1106. Min Act: -0.0000

Data Index: 196487 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 2.3340. Min Range: -2.3340

Max Act: 1.8848. Min Act: -0.0000

Data Index: 136123 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 2.3340. Min Range: -2.3340

Max Act: 1.9987. Min Act: -0.0000

Data Index: 1034662 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 2.3340. Min Range: -2.3340

Max Act: 1.9883. Min Act: -0.0000

Data Index: 708272 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 2.3340. Min Range: -2.3340

Max Act: 1.9835. Min Act: -0.0000

Data Index: 299618 (C4 (Web Text))

Max Activating Token Index: 758