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

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

Neuron 3352 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0001

Data Index: 126913 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0324. Min Act: -0.0001

Data Index: 68874 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0314. Min Act: -0.0001

Data Index: 1637054 (Python Code)

Max Activating Token Index: 29

Text #3

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0293. Min Act: -0.0001

Data Index: 969507 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0312. Min Act: -0.0001

Data Index: 850945 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0307. Min Act: -0.0001

Data Index: 734118 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0298. Min Act: -0.0001

Data Index: 381059 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0280. Min Act: -0.0001

Data Index: 683 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0286. Min Act: -0.0001

Data Index: 1011035 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0304. Min Act: -0.0001

Data Index: 197193 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0278. Min Act: -0.0001

Data Index: 404336 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0255. Min Act: -0.0001

Data Index: 802578 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0284. Min Act: -0.0001

Data Index: 1570740 (Python Code)

Max Activating Token Index: 626

Text #13

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0267. Min Act: -0.0001

Data Index: 967713 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0262. Min Act: -0.0001

Data Index: 212521 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0248. Min Act: -0.0001

Data Index: 1140861 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0252. Min Act: -0.0001

Data Index: 498401 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0286. Min Act: -0.0001

Data Index: 695773 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0257. Min Act: -0.0001

Data Index: 778982 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0257. Min Act: -0.0001

Data Index: 349007 (C4 (Web Text))

Max Activating Token Index: 489