Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 440 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.5586. Min Range: -3.5586

Max Act: 3.5586. Min Act: -0.1700

Data Index: 1435574 (Python Code)

Max Activating Token Index: 919

Text #1

Max Range: 3.5586. Min Range: -3.5586

Max Act: 3.4960. Min Act: -0.1700

Data Index: 1407231 (Python Code)

Max Activating Token Index: 243

Text #2

Max Range: 3.5586. Min Range: -3.5586

Max Act: 3.5116. Min Act: -0.1700

Data Index: 1419076 (Python Code)

Max Activating Token Index: 928

Text #3

Max Range: 3.5586. Min Range: -3.5586

Max Act: 3.4646. Min Act: -0.1700

Data Index: 1441029 (Python Code)

Max Activating Token Index: 197

Text #4

Max Range: 3.5586. Min Range: -3.5586

Max Act: 3.4803. Min Act: -0.1700

Data Index: 1416433 (Python Code)

Max Activating Token Index: 614

Text #5

Max Range: 3.5586. Min Range: -3.5586

Max Act: 3.4803. Min Act: -0.1700

Data Index: 1527692 (Python Code)

Max Activating Token Index: 358

Text #6

Max Range: 3.5586. Min Range: -3.5586

Max Act: 3.4646. Min Act: -0.1700

Data Index: 1547787 (Python Code)

Max Activating Token Index: 288

Text #7

Max Range: 3.5586. Min Range: -3.5586

Max Act: 3.4646. Min Act: -0.1700

Data Index: 1619206 (Python Code)

Max Activating Token Index: 609

Text #8

Max Range: 3.5586. Min Range: -3.5586

Max Act: 3.4646. Min Act: -0.1700

Data Index: 1621100 (Python Code)

Max Activating Token Index: 878

Text #9

Max Range: 3.5586. Min Range: -3.5586

Max Act: 3.4333. Min Act: -0.1700

Data Index: 1514062 (Python Code)

Max Activating Token Index: 144

Text #10

Max Range: 3.5586. Min Range: -3.5586

Max Act: 3.4490. Min Act: -0.1700

Data Index: 1510502 (Python Code)

Max Activating Token Index: 396

Text #11

Max Range: 3.5586. Min Range: -3.5586

Max Act: 3.4490. Min Act: -0.1700

Data Index: 1627197 (Python Code)

Max Activating Token Index: 52

Text #12

Max Range: 3.5586. Min Range: -3.5586

Max Act: 3.4176. Min Act: -0.1700

Data Index: 1493391 (Python Code)

Max Activating Token Index: 558

Text #13

Max Range: 3.5586. Min Range: -3.5586

Max Act: 3.4333. Min Act: -0.1700

Data Index: 1411890 (Python Code)

Max Activating Token Index: 964

Text #14

Max Range: 3.5586. Min Range: -3.5586

Max Act: 3.4490. Min Act: -0.1700

Data Index: 1360202 (Python Code)

Max Activating Token Index: 120

Text #15

Max Range: 3.5586. Min Range: -3.5586

Max Act: 3.4176. Min Act: -0.1700

Data Index: 1642608 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 3.5586. Min Range: -3.5586

Max Act: 3.4176. Min Act: -0.1700

Data Index: 1489198 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 3.5586. Min Range: -3.5586

Max Act: 3.4176. Min Act: -0.1700

Data Index: 1653114 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 3.5586. Min Range: -3.5586

Max Act: 3.4333. Min Act: -0.1700

Data Index: 1362346 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 3.5586. Min Range: -3.5586

Max Act: 3.4176. Min Act: -0.1700

Data Index: 1556528 (Python Code)

Max Activating Token Index: 600