Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 731 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.5060. Min Range: -5.5060

Max Act: 5.5060. Min Act: -0.1700

Data Index: 1522806 (Python Code)

Max Activating Token Index: 297

Text #1

Max Range: 5.5060. Min Range: -5.5060

Max Act: 5.4747. Min Act: -0.1700

Data Index: 1498172 (Python Code)

Max Activating Token Index: 162

Text #2

Max Range: 5.5060. Min Range: -5.5060

Max Act: 5.3810. Min Act: -0.1700

Data Index: 1492565 (Python Code)

Max Activating Token Index: 787

Text #3

Max Range: 5.5060. Min Range: -5.5060

Max Act: 5.3810. Min Act: -0.1700

Data Index: 1537857 (Python Code)

Max Activating Token Index: 437

Text #4

Max Range: 5.5060. Min Range: -5.5060

Max Act: 5.3185. Min Act: -0.1700

Data Index: 1652697 (Python Code)

Max Activating Token Index: 937

Text #5

Max Range: 5.5060. Min Range: -5.5060

Max Act: 5.2560. Min Act: -0.1700

Data Index: 1500242 (Python Code)

Max Activating Token Index: 729

Text #6

Max Range: 5.5060. Min Range: -5.5060

Max Act: 5.2247. Min Act: -0.1700

Data Index: 1524781 (Python Code)

Max Activating Token Index: 834

Text #7

Max Range: 5.5060. Min Range: -5.5060

Max Act: 5.2560. Min Act: -0.1700

Data Index: 1391421 (Python Code)

Max Activating Token Index: 985

Text #8

Max Range: 5.5060. Min Range: -5.5060

Max Act: 5.2247. Min Act: -0.1700

Data Index: 1558086 (Python Code)

Max Activating Token Index: 830

Text #9

Max Range: 5.5060. Min Range: -5.5060

Max Act: 5.2247. Min Act: -0.1700

Data Index: 1500265 (Python Code)

Max Activating Token Index: 928

Text #10

Max Range: 5.5060. Min Range: -5.5060

Max Act: 5.1622. Min Act: -0.1700

Data Index: 1388286 (Python Code)

Max Activating Token Index: 667

Text #11

Max Range: 5.5060. Min Range: -5.5060

Max Act: 5.2560. Min Act: -0.1700

Data Index: 1426219 (Python Code)

Max Activating Token Index: 973

Text #12

Max Range: 5.5060. Min Range: -5.5060

Max Act: 5.1310. Min Act: -0.1700

Data Index: 1540828 (Python Code)

Max Activating Token Index: 306

Text #13

Max Range: 5.5060. Min Range: -5.5060

Max Act: 5.1622. Min Act: -0.1700

Data Index: 1571457 (Python Code)

Max Activating Token Index: 342

Text #14

Max Range: 5.5060. Min Range: -5.5060

Max Act: 5.1310. Min Act: -0.1700

Data Index: 1484922 (Python Code)

Max Activating Token Index: 325

Text #15

Max Range: 5.5060. Min Range: -5.5060

Max Act: 5.1935. Min Act: -0.1700

Data Index: 1593174 (Python Code)

Max Activating Token Index: 178

Text #16

Max Range: 5.5060. Min Range: -5.5060

Max Act: 5.0997. Min Act: -0.1700

Data Index: 1533998 (Python Code)

Max Activating Token Index: 324

Text #17

Max Range: 5.5060. Min Range: -5.5060

Max Act: 5.1310. Min Act: -0.1700

Data Index: 1596001 (Python Code)

Max Activating Token Index: 678

Text #18

Max Range: 5.5060. Min Range: -5.5060

Max Act: 5.0997. Min Act: -0.1700

Data Index: 1571523 (Python Code)

Max Activating Token Index: 913

Text #19

Max Range: 5.5060. Min Range: -5.5060

Max Act: 5.0685. Min Act: -0.1700

Data Index: 1586764 (Python Code)

Max Activating Token Index: 964