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

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

Neuron 3017 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2458. Min Range: -3.2458

Max Act: 3.2458. Min Act: -0.0000

Data Index: 1476370 (Python Code)

Max Activating Token Index: 186

Text #1

Max Range: 3.2458. Min Range: -3.2458

Max Act: 3.0268. Min Act: -0.0000

Data Index: 1599101 (Python Code)

Max Activating Token Index: 41

Text #2

Max Range: 3.2458. Min Range: -3.2458

Max Act: 2.8173. Min Act: -0.0000

Data Index: 1450626 (Python Code)

Max Activating Token Index: 960

Text #3

Max Range: 3.2458. Min Range: -3.2458

Max Act: 2.8138. Min Act: -0.0000

Data Index: 1621617 (Python Code)

Max Activating Token Index: 30

Text #4

Max Range: 3.2458. Min Range: -3.2458

Max Act: 2.8295. Min Act: -0.0000

Data Index: 1573599 (Python Code)

Max Activating Token Index: 692

Text #5

Max Range: 3.2458. Min Range: -3.2458

Max Act: 2.6714. Min Act: -0.0000

Data Index: 1637825 (Python Code)

Max Activating Token Index: 949

Text #6

Max Range: 3.2458. Min Range: -3.2458

Max Act: 2.6620. Min Act: -0.0000

Data Index: 1375025 (Python Code)

Max Activating Token Index: 370

Text #7

Max Range: 3.2458. Min Range: -3.2458

Max Act: 2.5067. Min Act: -0.0000

Data Index: 1455943 (Python Code)

Max Activating Token Index: 611

Text #8

Max Range: 3.2458. Min Range: -3.2458

Max Act: 2.6346. Min Act: -0.0000

Data Index: 1645819 (Python Code)

Max Activating Token Index: 384

Text #9

Max Range: 3.2458. Min Range: -3.2458

Max Act: 2.5040. Min Act: -0.0000

Data Index: 1408605 (Python Code)

Max Activating Token Index: 262

Text #10

Max Range: 3.2458. Min Range: -3.2458

Max Act: 2.5815. Min Act: -0.0000

Data Index: 1570124 (Python Code)

Max Activating Token Index: 627

Text #11

Max Range: 3.2458. Min Range: -3.2458

Max Act: 2.4099. Min Act: -0.0000

Data Index: 1532157 (Python Code)

Max Activating Token Index: 349

Text #12

Max Range: 3.2458. Min Range: -3.2458

Max Act: 2.4935. Min Act: -0.0000

Data Index: 1412938 (Python Code)

Max Activating Token Index: 210

Text #13

Max Range: 3.2458. Min Range: -3.2458

Max Act: 2.1381. Min Act: -0.0000

Data Index: 1639807 (Python Code)

Max Activating Token Index: 265

Text #14

Max Range: 3.2458. Min Range: -3.2458

Max Act: 2.4796. Min Act: -0.0000

Data Index: 1445904 (Python Code)

Max Activating Token Index: 953

Text #15

Max Range: 3.2458. Min Range: -3.2458

Max Act: 2.4566. Min Act: -0.0000

Data Index: 1442670 (Python Code)

Max Activating Token Index: 14

Text #16

Max Range: 3.2458. Min Range: -3.2458

Max Act: 2.4164. Min Act: -0.0000

Data Index: 1438207 (Python Code)

Max Activating Token Index: 918

Text #17

Max Range: 3.2458. Min Range: -3.2458

Max Act: 2.3884. Min Act: -0.0000

Data Index: 1544247 (Python Code)

Max Activating Token Index: 230

Text #18

Max Range: 3.2458. Min Range: -3.2458

Max Act: 2.2996. Min Act: -0.0000

Data Index: 1537136 (Python Code)

Max Activating Token Index: 229

Text #19

Max Range: 3.2458. Min Range: -3.2458

Max Act: 2.4759. Min Act: -0.0000

Data Index: 1432698 (Python Code)

Max Activating Token Index: 300