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

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

Neuron 3119 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6970. Min Act: -0.0002

Data Index: 1616915 (Python Code)

Max Activating Token Index: 237

Text #1

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.7139. Min Act: -0.0002

Data Index: 1402157 (Python Code)

Max Activating Token Index: 281

Text #2

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6712. Min Act: -0.0002

Data Index: 1593292 (Python Code)

Max Activating Token Index: 108

Text #3

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6748. Min Act: -0.0002

Data Index: 1524460 (Python Code)

Max Activating Token Index: 196

Text #4

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6385. Min Act: -0.0002

Data Index: 1512602 (Python Code)

Max Activating Token Index: 360

Text #5

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6398. Min Act: -0.0002

Data Index: 1580325 (Python Code)

Max Activating Token Index: 801

Text #6

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6001. Min Act: -0.0002

Data Index: 1395422 (Python Code)

Max Activating Token Index: 173

Text #7

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6142. Min Act: -0.0002

Data Index: 1566704 (Python Code)

Max Activating Token Index: 736

Text #8

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.5905. Min Act: -0.0002

Data Index: 1364158 (Python Code)

Max Activating Token Index: 616

Text #9

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.5635. Min Act: -0.0002

Data Index: 1534740 (Python Code)

Max Activating Token Index: 376

Text #10

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.5706. Min Act: -0.0002

Data Index: 1444458 (Python Code)

Max Activating Token Index: 105

Text #11

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.5710. Min Act: -0.0002

Data Index: 1570274 (Python Code)

Max Activating Token Index: 309

Text #12

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.5838. Min Act: -0.0002

Data Index: 1639442 (Python Code)

Max Activating Token Index: 605

Text #13

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.5170. Min Act: -0.0002

Data Index: 1484129 (Python Code)

Max Activating Token Index: 304

Text #14

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.5587. Min Act: -0.0002

Data Index: 1469807 (Python Code)

Max Activating Token Index: 174

Text #15

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.5339. Min Act: -0.0002

Data Index: 1519792 (Python Code)

Max Activating Token Index: 646

Text #16

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.5667. Min Act: -0.0002

Data Index: 1423752 (Python Code)

Max Activating Token Index: 988

Text #17

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.5253. Min Act: -0.0002

Data Index: 1527485 (Python Code)

Max Activating Token Index: 981

Text #18

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.5574. Min Act: -0.0002

Data Index: 1404740 (Python Code)

Max Activating Token Index: 259

Text #19

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.5518. Min Act: -0.0002

Data Index: 1514646 (Python Code)

Max Activating Token Index: 438