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

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

Neuron 1306 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: 3.0891. Min Range: -3.0891

Max Act: 3.0891. Min Act: -0.1699

Data Index: 425087 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 3.0891. Min Range: -3.0891

Max Act: 3.0226. Min Act: -0.1700

Data Index: 540108 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 3.0891. Min Range: -3.0891

Max Act: 3.0290. Min Act: -0.1700

Data Index: 1522202 (Python Code)

Max Activating Token Index: 780

Text #3

Max Range: 3.0891. Min Range: -3.0891

Max Act: 3.0191. Min Act: -0.1680

Data Index: 1499686 (Python Code)

Max Activating Token Index: 296

Text #4

Max Range: 3.0891. Min Range: -3.0891

Max Act: 3.0078. Min Act: -0.1700

Data Index: 1443837 (Python Code)

Max Activating Token Index: 901

Text #5

Max Range: 3.0891. Min Range: -3.0891

Max Act: 2.9672. Min Act: -0.1685

Data Index: 1131434 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 3.0891. Min Range: -3.0891

Max Act: 2.9674. Min Act: -0.1699

Data Index: 1464816 (Python Code)

Max Activating Token Index: 613

Text #7

Max Range: 3.0891. Min Range: -3.0891

Max Act: 2.9806. Min Act: -0.1138

Data Index: 1598955 (Python Code)

Max Activating Token Index: 451

Text #8

Max Range: 3.0891. Min Range: -3.0891

Max Act: 2.9903. Min Act: -0.1636

Data Index: 1412581 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 3.0891. Min Range: -3.0891

Max Act: 2.9610. Min Act: -0.1521

Data Index: 879249 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 3.0891. Min Range: -3.0891

Max Act: 2.9519. Min Act: -0.1700

Data Index: 222282 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 3.0891. Min Range: -3.0891

Max Act: 2.9540. Min Act: -0.1688

Data Index: 1505348 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 3.0891. Min Range: -3.0891

Max Act: 2.9366. Min Act: -0.1138

Data Index: 1560984 (Python Code)

Max Activating Token Index: 626

Text #13

Max Range: 3.0891. Min Range: -3.0891

Max Act: 2.9332. Min Act: -0.1697

Data Index: 1529289 (Python Code)

Max Activating Token Index: 719

Text #14

Max Range: 3.0891. Min Range: -3.0891

Max Act: 2.9289. Min Act: -0.1138

Data Index: 1378790 (Python Code)

Max Activating Token Index: 700

Text #15

Max Range: 3.0891. Min Range: -3.0891

Max Act: 2.9518. Min Act: -0.1677

Data Index: 42356 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 3.0891. Min Range: -3.0891

Max Act: 2.9346. Min Act: -0.1676

Data Index: 1227923 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 3.0891. Min Range: -3.0891

Max Act: 2.9488. Min Act: -0.1213

Data Index: 1291647 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 3.0891. Min Range: -3.0891

Max Act: 2.9337. Min Act: -0.1699

Data Index: 188046 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 3.0891. Min Range: -3.0891

Max Act: 2.8963. Min Act: -0.1684

Data Index: 730179 (C4 (Web Text))

Max Activating Token Index: 308