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

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

Neuron 177 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: 4.8121. Min Range: -4.8121

Max Act: 4.8121. Min Act: -0.1700

Data Index: 1596195 (Python Code)

Max Activating Token Index: 521

Text #1

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.6790. Min Act: -0.1700

Data Index: 1080532 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.6758. Min Act: -0.1694

Data Index: 1176256 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.6247. Min Act: -0.1700

Data Index: 83722 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.6467. Min Act: -0.1700

Data Index: 1380464 (Python Code)

Max Activating Token Index: 727

Text #5

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.6179. Min Act: -0.1699

Data Index: 1548745 (Python Code)

Max Activating Token Index: 799

Text #6

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.5922. Min Act: -0.1699

Data Index: 1471431 (Python Code)

Max Activating Token Index: 884

Text #7

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.6159. Min Act: -0.1700

Data Index: 1654181 (Python Code)

Max Activating Token Index: 785

Text #8

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.5855. Min Act: -0.1699

Data Index: 1428656 (Python Code)

Max Activating Token Index: 948

Text #9

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.5600. Min Act: -0.1700

Data Index: 1425483 (Python Code)

Max Activating Token Index: 660

Text #10

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.4841. Min Act: -0.1699

Data Index: 1183985 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.4896. Min Act: -0.1700

Data Index: 1619906 (Python Code)

Max Activating Token Index: 746

Text #12

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.5095. Min Act: -0.1700

Data Index: 1618332 (Python Code)

Max Activating Token Index: 999

Text #13

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.4864. Min Act: -0.1699

Data Index: 955656 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.5088. Min Act: -0.1700

Data Index: 155599 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.4459. Min Act: -0.1700

Data Index: 1461793 (Python Code)

Max Activating Token Index: 564

Text #16

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.4104. Min Act: -0.1700

Data Index: 1504160 (Python Code)

Max Activating Token Index: 615

Text #17

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.4657. Min Act: -0.1695

Data Index: 1461583 (Python Code)

Max Activating Token Index: 600

Text #18

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.4310. Min Act: -0.1700

Data Index: 126682 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.4104. Min Act: -0.1700

Data Index: 1612599 (Python Code)

Max Activating Token Index: 747