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

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

Neuron 434 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3847. Min Range: -3.3847

Max Act: 3.3847. Min Act: -0.1700

Data Index: 1621193 (Python Code)

Max Activating Token Index: 170

Text #1

Max Range: 3.3847. Min Range: -3.3847

Max Act: 3.3533. Min Act: -0.1700

Data Index: 1395323 (Python Code)

Max Activating Token Index: 244

Text #2

Max Range: 3.3847. Min Range: -3.3847

Max Act: 3.3219. Min Act: -0.1700

Data Index: 1419235 (Python Code)

Max Activating Token Index: 356

Text #3

Max Range: 3.3847. Min Range: -3.3847

Max Act: 3.3219. Min Act: -0.1700

Data Index: 1522532 (Python Code)

Max Activating Token Index: 206

Text #4

Max Range: 3.3847. Min Range: -3.3847

Max Act: 3.3219. Min Act: -0.1700

Data Index: 1401163 (Python Code)

Max Activating Token Index: 561

Text #5

Max Range: 3.3847. Min Range: -3.3847

Max Act: 3.3062. Min Act: -0.1700

Data Index: 1452947 (Python Code)

Max Activating Token Index: 892

Text #6

Max Range: 3.3847. Min Range: -3.3847

Max Act: 3.3376. Min Act: -0.1700

Data Index: 1504112 (Python Code)

Max Activating Token Index: 271

Text #7

Max Range: 3.3847. Min Range: -3.3847

Max Act: 3.2905. Min Act: -0.1700

Data Index: 1472595 (Python Code)

Max Activating Token Index: 6

Text #8

Max Range: 3.3847. Min Range: -3.3847

Max Act: 3.2748. Min Act: -0.1700

Data Index: 1597553 (Python Code)

Max Activating Token Index: 669

Text #9

Max Range: 3.3847. Min Range: -3.3847

Max Act: 3.2591. Min Act: -0.1700

Data Index: 1574315 (Python Code)

Max Activating Token Index: 386

Text #10

Max Range: 3.3847. Min Range: -3.3847

Max Act: 3.2277. Min Act: -0.1700

Data Index: 1477383 (Python Code)

Max Activating Token Index: 11

Text #11

Max Range: 3.3847. Min Range: -3.3847

Max Act: 3.2591. Min Act: -0.1700

Data Index: 1611979 (Python Code)

Max Activating Token Index: 484

Text #12

Max Range: 3.3847. Min Range: -3.3847

Max Act: 3.2119. Min Act: -0.1700

Data Index: 1633761 (Python Code)

Max Activating Token Index: 199

Text #13

Max Range: 3.3847. Min Range: -3.3847

Max Act: 3.2119. Min Act: -0.1700

Data Index: 1499230 (Python Code)

Max Activating Token Index: 1010

Text #14

Max Range: 3.3847. Min Range: -3.3847

Max Act: 3.1962. Min Act: -0.1700

Data Index: 1507432 (Python Code)

Max Activating Token Index: 140

Text #15

Max Range: 3.3847. Min Range: -3.3847

Max Act: 3.1962. Min Act: -0.1700

Data Index: 1398681 (Python Code)

Max Activating Token Index: 335

Text #16

Max Range: 3.3847. Min Range: -3.3847

Max Act: 3.1805. Min Act: -0.1700

Data Index: 1583100 (Python Code)

Max Activating Token Index: 327

Text #17

Max Range: 3.3847. Min Range: -3.3847

Max Act: 3.1805. Min Act: -0.1700

Data Index: 1558657 (Python Code)

Max Activating Token Index: 92

Text #18

Max Range: 3.3847. Min Range: -3.3847

Max Act: 3.1647. Min Act: -0.1700

Data Index: 1602057 (Python Code)

Max Activating Token Index: 116

Text #19

Max Range: 3.3847. Min Range: -3.3847

Max Act: 3.1805. Min Act: -0.1700

Data Index: 1603450 (Python Code)

Max Activating Token Index: 384