Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 435 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.0004. Min Range: -3.0004

Max Act: 3.0004. Min Act: -0.1700

Data Index: 1610012 (Python Code)

Max Activating Token Index: 334

Text #1

Max Range: 3.0004. Min Range: -3.0004

Max Act: 2.9224. Min Act: -0.1700

Data Index: 1581586 (Python Code)

Max Activating Token Index: 568

Text #2

Max Range: 3.0004. Min Range: -3.0004

Max Act: 2.8550. Min Act: -0.1700

Data Index: 9564 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 3.0004. Min Range: -3.0004

Max Act: 2.8340. Min Act: -0.1700

Data Index: 1593075 (Python Code)

Max Activating Token Index: 61

Text #4

Max Range: 3.0004. Min Range: -3.0004

Max Act: 2.8216. Min Act: -0.1700

Data Index: 1572900 (Python Code)

Max Activating Token Index: 609

Text #5

Max Range: 3.0004. Min Range: -3.0004

Max Act: 2.8020. Min Act: -0.1700

Data Index: 1458593 (Python Code)

Max Activating Token Index: 848

Text #6

Max Range: 3.0004. Min Range: -3.0004

Max Act: 2.7791. Min Act: -0.1700

Data Index: 1429285 (Python Code)

Max Activating Token Index: 292

Text #7

Max Range: 3.0004. Min Range: -3.0004

Max Act: 2.7784. Min Act: -0.1700

Data Index: 1363943 (Python Code)

Max Activating Token Index: 526

Text #8

Max Range: 3.0004. Min Range: -3.0004

Max Act: 2.7621. Min Act: -0.1700

Data Index: 1507977 (Python Code)

Max Activating Token Index: 903

Text #9

Max Range: 3.0004. Min Range: -3.0004

Max Act: 2.7601. Min Act: -0.1700

Data Index: 1375954 (Python Code)

Max Activating Token Index: 682

Text #10

Max Range: 3.0004. Min Range: -3.0004

Max Act: 2.7741. Min Act: -0.1700

Data Index: 1397121 (Python Code)

Max Activating Token Index: 661

Text #11

Max Range: 3.0004. Min Range: -3.0004

Max Act: 2.7609. Min Act: -0.1700

Data Index: 1622254 (Python Code)

Max Activating Token Index: 481

Text #12

Max Range: 3.0004. Min Range: -3.0004

Max Act: 2.7700. Min Act: -0.1700

Data Index: 1574398 (Python Code)

Max Activating Token Index: 960

Text #13

Max Range: 3.0004. Min Range: -3.0004

Max Act: 2.7664. Min Act: -0.1700

Data Index: 1363121 (Python Code)

Max Activating Token Index: 987

Text #14

Max Range: 3.0004. Min Range: -3.0004

Max Act: 2.7661. Min Act: -0.1700

Data Index: 1492194 (Python Code)

Max Activating Token Index: 171

Text #15

Max Range: 3.0004. Min Range: -3.0004

Max Act: 2.7373. Min Act: -0.1700

Data Index: 1566551 (Python Code)

Max Activating Token Index: 536

Text #16

Max Range: 3.0004. Min Range: -3.0004

Max Act: 2.7362. Min Act: -0.1700

Data Index: 1624040 (Python Code)

Max Activating Token Index: 832

Text #17

Max Range: 3.0004. Min Range: -3.0004

Max Act: 2.7339. Min Act: -0.1700

Data Index: 1434816 (Python Code)

Max Activating Token Index: 325

Text #18

Max Range: 3.0004. Min Range: -3.0004

Max Act: 2.7004. Min Act: -0.1700

Data Index: 259452 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 3.0004. Min Range: -3.0004

Max Act: 2.7287. Min Act: -0.1700

Data Index: 1484036 (Python Code)

Max Activating Token Index: 529